docs: name the benchmarks computed from our dataset (review)

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

backend/app.py

@@ -97,8 +97,9 @@ STATIC_SITEMAP_PATHS = ("/", "/rankings", "/compare", "/admissions")
 
 # A page has something a search result could state if any of these is present
 # in any year. Shared by _has_publishable_data and the per-school check in
-# _school_sitemap_rows so the two can never drift.
-_PUBLISHABLE_FIELDS = ("rwm_expected_pct", "attainment_8_score", "ofsted_grade")
+# _school_sitemap_rows so the two can never drift. An inspection with no
+# overall grade (ofsted_date alone) still gives a page something to state.
+_PUBLISHABLE_FIELDS = ("rwm_expected_pct", "attainment_8_score", "ofsted_grade", "ofsted_date")
 
 
 def _has_publishable_data(row) -> bool:

backend/data_loader.py

@@ -18,7 +18,7 @@ from .config import settings
 from .database import SessionLocal, engine
 from .models import (
     DimSchool, DimLocation, KS2Performance,
-    FactOfstedInspection, FactAdmissions, FactAdmissionDistance,
+    FactOfstedLatest, FactAdmissions, FactAdmissionDistance,
     FactDeprivation, FactFinance, FactPupilCharacteristics,
     FactKs4Destinations, FactKs5Destinations,
 )
@@ -251,10 +251,11 @@ _MAIN_QUERY = text("""
         s.website,
         s.telephone,
         s.nursery_provision,
-        foi.ofsted_grade,
-        foi.ofsted_date,
-        foi.ofsted_framework,
-        foi.ofsted_rc_date,
+        foi.current_grade         AS ofsted_grade,
+        foi.current_grade_date    AS ofsted_grade_date,
+        foi.latest_visit_date     AS ofsted_date,
+        foi.framework             AS ofsted_framework,
+        foi.rc_inspection_date    AS ofsted_rc_date,
         l.local_authority_name AS local_authority,
         l.local_authority_code,
         l.address_line1        AS address1,
@@ -335,21 +336,10 @@ _MAIN_QUERY = text("""
     FROM marts.dim_school s
     JOIN marts.dim_location l ON s.urn = l.urn
     LEFT JOIN marts.fact_performance p ON s.urn = p.urn
-    LEFT JOIN (
-        SELECT DISTINCT ON (urn)
-            urn,
-            -- Fall back to the ungraded-inspection grade when no graded grade exists.
-            COALESCE(overall_effectiveness, ungraded_grade) AS ofsted_grade,
-            inspection_date       AS ofsted_date,
-            framework             AS ofsted_framework,
-            -- Report-card signal for list/map badges: non-null only when the
-            -- latest inspection carries report-card grades. framework is the
-            -- raw event grouping ("Schools - S5"), never "ReportCard", so it
-            -- can't be used to detect report cards.
-            rc_inspection_date    AS ofsted_rc_date
-        FROM marts.fact_ofsted_inspection
-        ORDER BY urn, inspection_date DESC NULLS LAST
-    ) foi ON s.urn = foi.urn
+    -- One current Ofsted status per school (pipeline: int_ofsted_latest): the
+    -- grade still in force, dated by the inspection that awarded or confirmed
+    -- it, and the latest visit of any kind.
+    LEFT JOIN marts.fact_ofsted_latest foi ON s.urn = foi.urn
     ORDER BY s.school_name, p.year
 """)
 
@@ -731,39 +721,36 @@ def compute_benchmarks(df: pd.DataFrame, census_benchmarks: dict | None = None)
     }
 
 
+def _iso(d):
+    return d.isoformat() if d else None
+
+
 def _ofsted_block(o, urn: int) -> dict:
-    """Serialize the latest Ofsted inspection row for API responses.
+    """Serialize a fact_ofsted_latest row for API responses.
 
-    `grade_source` records where the effective overall grade came from:
-    a graded (Section 5) inspection, or carried forward from an ungraded
-    (Section 8) outcome — materially different claims a UI must be able
-    to distinguish. `report_card` holds coded+labelled renewed-framework
-    (Nov 2025) area judgements; safeguarding is a separate boolean and
-    never appears among the graded areas.
+    `current_grade` is the overall grade still in force, dated by the
+    inspection that awarded or confirmed it; `latest_visit` is the school's
+    most recent inspection of any kind. The rule lives in int_ofsted_latest
+    (docs/superpowers/specs/2026-10-05-ofsted-current-status-design.md).
+    `overall_effectiveness` and `inspection_date` describe the graded
+    inspection itself and label its area judgements. `report_card` holds the
+    renewed-framework (Nov 2025) area judgements; safeguarding is a separate
+    boolean and never appears among the graded areas.
     """
-    if o.overall_effectiveness is not None:
-        grade_source = "graded"
-        overall = o.overall_effectiveness
-    elif o.ungraded_grade is not None:
-        # Fall back to the grade parsed from an ungraded (Section 8) outcome
-        # (e.g. "School remains Good") so the detail page matches the list badge.
-        grade_source = "ungraded_carried_forward"
-        overall = o.ungraded_grade
-    else:
-        grade_source = None
-        overall = None
-
     block = {
         "framework": o.framework,
-        "inspection_date": o.inspection_date.isoformat() if o.inspection_date else None,
-        "rc_inspection_date": (
-            o.rc_inspection_date.isoformat()
-            if getattr(o, "rc_inspection_date", None)
-            else None
-        ),
+        "inspection_date": _iso(o.graded_inspection_date),
+        "rc_inspection_date": _iso(o.rc_inspection_date),
         "inspection_type": o.inspection_type,
-        "overall_effectiveness": overall,
-        "grade_source": grade_source,
+        "overall_effectiveness": o.overall_effectiveness if o.overall_effectiveness in (1, 2, 3, 4) else None,
+        "current_grade": (
+            {"grade": o.current_grade, "date": _iso(o.current_grade_date), "basis": o.current_grade_basis}
+            if o.current_grade is not None else None
+        ),
+        "latest_visit": (
+            {"date": _iso(o.latest_visit_date), "kind": o.latest_visit_kind, "outcome": o.latest_visit_outcome}
+            if o.latest_visit_date else None
+        ),
         "quality_of_education": o.quality_of_education,
         "behaviour_attitudes": o.behaviour_attitudes,
         "personal_development": o.personal_development,
@@ -1097,20 +1084,14 @@ def get_supplementary_data_batch(db: Session, urns: list[int]) -> dict:
             logging.getLogger(__name__).error("batch supplementary query failed: %s", e)
             db.rollback()
 
-    # Ofsted — latest inspection per URN. Ordered so the first row seen per
-    # URN is the most recent.
+    # Ofsted — the mart already holds one current status per URN.
     def _ofsted():
         rows = (
-            db.query(FactOfstedInspection)
-            .filter(FactOfstedInspection.urn.in_(urns))
-            .order_by(FactOfstedInspection.urn, FactOfstedInspection.inspection_date.desc())
+            db.query(FactOfstedLatest)
+            .filter(FactOfstedLatest.urn.in_(urns))
             .all()
         )
-        seen = set()
         for o in rows:
-            if o.urn in seen:
-                continue
-            seen.add(o.urn)
             result[o.urn]["ofsted"] = _ofsted_block(o, o.urn)
     _safe(_ofsted)
 

backend/models.py

@@ -162,6 +162,49 @@ class FactOfstedInspection(Base):
     report_url = Column(Text)
 
 
+class FactOfstedLatest(Base):
+    """Current Ofsted status — one row per URN (pipeline: int_ofsted_latest).
+
+    `current_grade` is the overall grade still in force, dated by the
+    inspection that awarded or confirmed it; `latest_visit_*` is the school's
+    most recent inspection of any kind.
+    """
+    __tablename__ = "fact_ofsted_latest"
+    __table_args__ = MARTS
+
+    urn = Column(Integer, primary_key=True)
+    latest_visit_date = Column(Date)
+    latest_visit_kind = Column(String(20))
+    latest_visit_outcome = Column(String(100))
+    current_grade = Column(Integer)
+    current_grade_date = Column(Date)
+    current_grade_basis = Column(String(20))
+    graded_inspection_date = Column(Date)
+    ungraded_inspection_date = Column(Date)
+    rc_inspection_date = Column(Date)
+    inspection_type = Column(String(100))
+    framework = Column(String(20))
+    overall_effectiveness = Column(Integer)
+    quality_of_education = Column(Integer)
+    behaviour_attitudes = Column(Integer)
+    personal_development = Column(Integer)
+    leadership_management = Column(Integer)
+    early_years_provision = Column(Integer)
+    sixth_form_provision = Column(Integer)
+    ungraded_outcome = Column(String(100))
+    ungraded_grade = Column(Integer)
+    rc_safeguarding_met = Column(Boolean)
+    rc_inclusion = Column(Integer)
+    rc_curriculum_teaching = Column(Integer)
+    rc_achievement = Column(Integer)
+    rc_attendance_behaviour = Column(Integer)
+    rc_personal_development = Column(Integer)
+    rc_leadership_governance = Column(Integer)
+    rc_early_years = Column(Integer)
+    rc_sixth_form = Column(Integer)
+    report_url = Column(Text)
+
+
 class FactAdmissions(Base):
     """School admissions — one row per URN per year."""
     __tablename__ = "fact_admissions"

backend/schemas.py

@@ -574,6 +574,7 @@ SCHOOL_COLUMNS = [
     "gender",
     "admissions_policy",
     "ofsted_grade",
+    "ofsted_grade_date",
     "ofsted_date",
     "ofsted_framework",
     "ofsted_rc_date",

backend/tests/test_compare_enrichment.py

@@ -12,7 +12,8 @@ from fastapi.testclient import TestClient
 LATEST = 202425
 
 CANNED_SUPPLEMENTARY = {
-    "ofsted": {"overall_effectiveness": 2, "grade_source": "graded",
+    "ofsted": {"overall_effectiveness": 2,
+               "current_grade": {"grade": 2, "date": "2023-01-01", "basis": "graded"},
                "report_card": {}, "ofsted_page_url": "https://reports.ofsted.gov.uk/provider/21/100140"},
     "census": {"year": 202526, "fsm_pct": 29.8},
     "admissions": {"year": 202627, "second_preference_offers": 4},
@@ -86,7 +87,7 @@ def test_each_school_gains_supplementary_blocks(client):
     body = client.get("/api/compare?urns=100140,138690").json()
     for urn in ("100140", "138690"):
         school = body["comparison"][urn]
-        assert school["ofsted"]["grade_source"] == "graded"
+        assert school["ofsted"]["current_grade"]["basis"] == "graded"
         assert school["census"]["fsm_pct"] == 29.8
         assert school["admissions"]["second_preference_offers"] == 4
         assert school["admissions_history"][0]["year"] == 202627

backend/tests/test_ofsted_status_payload.py

@@ -0,0 +1,56 @@
+"""The search badge reads ofsted_grade, ofsted_grade_date and ofsted_date from
+list rows (nextjs-app/lib/utils.ts buildOfstedListBadge). A field the list
+never sends would leave the badge without its year, or worse, fall back to
+"Not yet inspected". The school page reads current_grade and latest_visit from
+the ofsted block (lib/ofstedStatus.ts)."""
+
+import numpy as np
+import pandas as pd
+import pytest
+from fastapi.testclient import TestClient
+
+from backend.schemas import SCHOOL_COLUMNS
+
+
+def test_list_columns_include_the_status_fields():
+    for field in ("ofsted_grade", "ofsted_grade_date", "ofsted_date", "ofsted_rc_date"):
+        assert field in SCHOOL_COLUMNS
+
+
+def _df() -> pd.DataFrame:
+    # Rabbsfarm (102408): latest inspection 17 June 2025 gave no overall grade.
+    return pd.DataFrame([{
+        "urn": 102408, "school_name": "Rabbsfarm Primary School", "phase": "Primary",
+        "school_type": "Community school", "local_authority": "Hillingdon",
+        "address": "Gordon Road, Yiewsley, UB7 8AH", "postcode": "UB7 8AH",
+        "latitude": 51.51, "longitude": -0.47, "year": 202425, "rwm_expected_pct": 58.0,
+        "total_pupils": 60, "gias_total_pupils": 616,
+        "ofsted_grade": np.nan, "ofsted_grade_date": None, "ofsted_date": "2025-06-17",
+        "ofsted_framework": "Schools - S5", "ofsted_rc_date": None,
+    }])
+
+
+@pytest.fixture()
+def client(monkeypatch):
+    from backend import app as app_module
+
+    monkeypatch.setattr(app_module, "load_school_data", _df)
+    monkeypatch.setattr(app_module, "load_latest_school_data", _df)
+    monkeypatch.setattr(app_module, "_place_registry", None)
+    return TestClient(app_module.app, raise_server_exceptions=False)
+
+
+def test_search_rows_carry_the_status_fields(client):
+    resp = client.get("/api/schools")
+    assert resp.status_code == 200, resp.text
+    row = resp.json()["schools"][0]
+    assert row["ofsted_grade"] is None
+    assert row["ofsted_date"] == "2025-06-17"
+    assert "ofsted_grade_date" in row
+
+
+def test_a_school_with_only_an_inspection_is_publishable():
+    from backend.app import _has_publishable_data
+
+    assert _has_publishable_data({"rwm_expected_pct": None, "attainment_8_score": None,
+                                  "ofsted_grade": None, "ofsted_date": "2025-06-17"})

backend/tests/test_supplementary_batch.py

@@ -85,12 +85,15 @@ def _ofsted_row(urn, date, oe):
         "framework", "inspection_type", "quality_of_education", "behaviour_attitudes",
         "personal_development", "leadership_management", "early_years_provision",
         "sixth_form_provision", "ungraded_outcome", "ungraded_grade",
+        "ungraded_inspection_date", "rc_inspection_date", "latest_visit_outcome",
         "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)
+    when = types.SimpleNamespace(isoformat=lambda: date)
+    base.update(urn=urn, graded_inspection_date=when, latest_visit_date=when,
+                latest_visit_kind="graded", overall_effectiveness=oe,
+                current_grade=oe, current_grade_date=when, current_grade_basis="graded")
     return types.SimpleNamespace(**base)
 
 
@@ -114,10 +117,9 @@ def _dist_row(urn, year, distance_m, route_count=1):
 
 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": [
+        # The mart holds one current Ofsted status per URN.
+        "FactOfstedLatest": [
             _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)],
@@ -142,14 +144,14 @@ def test_one_query_per_table_and_latest_row_per_urn():
     assert sorted(session.queries) == [
         "FactAdmissionDistance", "FactAdmissions", "FactDeprivation",
         "FactFinance", "FactKs4Destinations", "FactKs5Destinations",
-        "FactOfstedInspection", "FactPupilCharacteristics",
+        "FactOfstedLatest", "FactPupilCharacteristics",
     ]
 
     # A school with no destination rows gets null, not an empty shell — the
     # frontend renders the section from the block's presence.
     assert out[1]["destinations"] is None
 
-    # Latest Ofsted kept per URN
+    # Each URN's current Ofsted status
     assert out[1]["ofsted"]["overall_effectiveness"] == 2
     assert out[2]["ofsted"]["overall_effectiveness"] == 1
 
@@ -175,7 +177,7 @@ def test_one_query_per_table_and_latest_row_per_urn():
 
 
 def test_single_wrapper_matches_batch(monkeypatch):
-    session = _FakeSession({"FactOfstedInspection": [_ofsted_row(5, "2022-01-01", 2)]})
+    session = _FakeSession({"FactOfstedLatest": [_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"] == []

backend/tests/test_supplementary_enrichment.py

@@ -10,7 +10,10 @@ from backend.data_loader import _admissions_row_dict, _ofsted_block
 
 def _row(**kw):
     base = dict(
-        framework="RC", inspection_date=None, inspection_type=None,
+        framework="RC", inspection_type=None,
+        graded_inspection_date=None, ungraded_inspection_date=None, rc_inspection_date=None,
+        latest_visit_date=None, latest_visit_kind=None, latest_visit_outcome=None,
+        current_grade=None, current_grade_date=None, current_grade_basis=None,
         overall_effectiveness=None, quality_of_education=None,
         behaviour_attitudes=None, personal_development=None,
         leadership_management=None, early_years_provision=None,
@@ -33,20 +36,41 @@ def test_report_card_block_and_provider_url():
     assert block["ofsted_page_url"] == "https://reports.ofsted.gov.uk/provider/21/100140"
 
 
-def test_grade_source_graded_vs_carried_forward():
-    assert _ofsted_block(_row(overall_effectiveness=1), urn=1)["grade_source"] == "graded"
-    carried = _ofsted_block(_row(ungraded_grade=2), urn=1)
-    assert carried["grade_source"] == "ungraded_carried_forward"
-    assert carried["overall_effectiveness"] == 2
-    assert _ofsted_block(_row(), urn=1)["grade_source"] is None
+def test_no_grade_is_carried_past_a_newer_inspection():
+    # Rabbsfarm (102408): the 2025 inspection gave no overall grade.
+    block = _ofsted_block(_row(
+        graded_inspection_date=date(2025, 6, 17), ungraded_inspection_date=date(2020, 2, 6),
+        latest_visit_date=date(2025, 6, 17), latest_visit_kind="graded",
+        ungraded_grade=2, ungraded_outcome="School remains Good", quality_of_education=3,
+    ), urn=102408)
+    assert block["current_grade"] is None
+    assert block["overall_effectiveness"] is None
+    assert block["latest_visit"] == {"date": "2025-06-17", "kind": "graded", "outcome": None}
+    assert block["inspection_date"] == "2025-06-17"
+    assert "grade_source" not in block
+
+
+def test_confirmed_grade_is_dated_by_the_confirming_visit():
+    block = _ofsted_block(_row(
+        graded_inspection_date=date(2020, 1, 7), ungraded_inspection_date=date(2024, 7, 18),
+        latest_visit_date=date(2024, 7, 18), latest_visit_kind="ungraded",
+        latest_visit_outcome="School remains Good", overall_effectiveness=2,
+        current_grade=2, current_grade_date=date(2024, 7, 18), current_grade_basis="confirmed",
+    ), urn=104762)
+    assert block["current_grade"] == {"grade": 2, "date": "2024-07-18", "basis": "confirmed"}
+    assert block["overall_effectiveness"] == 2
+    assert block["inspection_date"] == "2020-01-07"
+
+
+def test_overall_sentinel_is_not_served_as_a_grade():
+    assert _ofsted_block(_row(overall_effectiveness=9), urn=1)["overall_effectiveness"] is None
 
 
 def test_ofsted_block_carries_rc_inspection_date():
     o = _row(
-        ungraded_grade=2,
         rc_achievement=1,
         rc_inspection_date=date(2026, 2, 3),
-        inspection_date=date(2021, 10, 7),
+        graded_inspection_date=date(2021, 10, 7),
     )
     block = _ofsted_block(o, urn=138690)
     assert block["rc_inspection_date"] == "2026-02-03"
@@ -55,7 +79,7 @@ def test_ofsted_block_carries_rc_inspection_date():
 
 
 def test_ofsted_block_rc_inspection_date_none_when_absent():
-    o = _row(overall_effectiveness=1, inspection_date=date(2021, 10, 13))
+    o = _row(overall_effectiveness=1, graded_inspection_date=date(2021, 10, 13))
     block = _ofsted_block(o, urn=136276)
     assert block["rc_inspection_date"] is None
 
@@ -63,6 +87,7 @@ def test_ofsted_block_rc_inspection_date_none_when_absent():
 def test_ofsted_block_keeps_existing_keys():
     block = _ofsted_block(_row(overall_effectiveness=2, quality_of_education=2), urn=1)
     for key in ("framework", "inspection_date", "overall_effectiveness",
+                "current_grade", "latest_visit",
                 "quality_of_education", "rc_inclusion", "report_url"):
         assert key in block
 

docs/ARCHITECTURE.md

@@ -61,6 +61,12 @@ history from the full DataFrame and supplementary data from marts. Comparisons
 batch supplementary queries across selected URNs. Async routes still contain
 synchronous dependency calls; a fully asynchronous database layer is not present.
 
+DfE's official benchmarks live in marts: `fact_ks2_national_averages` and
+`fact_ks4_national_averages` for England, and `fact_ks4_la_averages` (all
+state-funded schools, per LA) for the search rows' "vs LA avg".
+`data_loader.compute_benchmarks` computes further state-school benchmarks from
+our own dataset; they are not DfE figures and are labelled as computed.
+
 ## Frontend boundaries
 
 `app/(frontend)` owns the public root layout and pages. `app/(payload)` owns the

docs/superpowers/specs/2026-10-05-ofsted-current-status-design.md

@@ -0,0 +1,257 @@
+# Ofsted Current Status — Design
+
+**Date:** 2026-10-05
+**Status:** approved design, not yet implemented
+**Scope:** `pipeline/transform` Ofsted models, `backend/data_loader.py`, list and
+detail API Ofsted fields, search and map badges, school-page Ofsted section,
+compare Ofsted rows, Typesense rating, sitemap
+**Fixes:** audit findings C1, M1 and (as a side effect) M2 and part of H3,
+from the 3 Oct 2026 accuracy audit
+
+## Goal
+
+Never show an Ofsted grade under a date it was not awarded or confirmed on, and
+always date "Inspected" by the school's latest visit.
+
+## The problem
+
+Ofsted's management information gives each school at most three inspections:
+the latest graded inspection (date G, an overall grade or "Not judged", area
+grades), the latest ungraded inspection (date U, an outcome sentence) and the
+latest report card (date RC).
+
+The site derives a grade and a date from these with two independent rules:
+
+- grade = the graded inspection's overall grade, or else the grade parsed from
+  the ungraded outcome ("School remains Good" → 2);
+- date = G, or else U.
+
+The two rules can pick different inspections. Every inspection from
+September 2024 to November 2025 was graded with "Not judged" overall, so the
+grade falls back to an older ungraded visit while the date stays the new one.
+
+- **C1.** Rabbsfarm Primary School (102408) shows "Good · 2025". Ofsted's
+  17 June 2025 inspection gave no overall grade and rated quality of education,
+  behaviour and leadership Requires Improvement. The "Good" comes from an
+  ungraded visit on 6 February 2020. Site-wide, 932 badges pair a
+  carried-forward grade with a newer inspection's year, and 147 of them say Good
+  or Outstanding while that inspection rated an area Requires Improvement or
+  Inadequate. Acre Wood Academy (151783) reads "Good · 2024" though the
+  October 2024 inspection rated all four areas Inadequate.
+- **M1.** When a newer ungraded visit exists, the page shows the older graded
+  date. Washwood Heath Academy (139888) reads "Inspected 3 Mar 2020 · 4+ years
+  ago"; Ofsted visited on 21 May 2025. 667 schools.
+
+Ofsted's own provider page for Rabbsfarm leads with the 2025 area judgements and
+"From September 2024, Ofsted no longer makes an overall effectiveness
+judgement". It shows no overall grade.
+
+The rule is also implemented four times: `dim_school.ofsted_grade` (feeds
+Typesense), the list SQL in `data_loader.py`, `_ofsted_block`, and two separate
+"latest row" picks over `marts.fact_ofsted_inspection` by `inspection_date`,
+which tie arbitrarily on duplicate monthly rows.
+
+## Non-goals
+
+- Predecessor inspections (audit M10): a grade Ofsted attributes to a previous
+  URN stays unlabelled.
+- Post-16 and ISI-inspected schools (H4) and the "Not yet inspected" label.
+- The compare page's broken Ofsted link (M4).
+- Report-card display, which is unchanged.
+
+## The rule
+
+Computed once per URN in `int_ofsted_latest`.
+
+**Latest visit:** the newest of RC, G and U.
+
+- `latest_visit_date`
+- `latest_visit_kind`: `report_card`, `graded` or `ungraded`
+- `latest_visit_outcome`: the ungraded outcome text when the kind is `ungraded`,
+  otherwise null
+
+**Current grade:** the overall grade still in force, if any.
+
+| Situation | `current_grade` | `current_grade_date` | `current_grade_basis` |
+|---|---|---|---|
+| A report card exists | null | null | null |
+| Latest is graded, overall 1–4 | that grade | G | `graded` |
+| Latest is graded, "Not judged" | null | null | null |
+| Latest is ungraded, outcome "School remains X…" (any qualifier) | X | U | `confirmed` |
+| Latest is ungraded, any other outcome ("Standards maintained", "Improved significantly", "Some aspects not as strong") | the graded inspection's overall grade if it is 1–4, else null | G when a grade is kept | `graded` when a grade is kept |
+| No inspection | null | null | null |
+
+A report card replaced overall grades, so no legacy grade stays in force beside
+one. The latest visit is read from the dates, not assumed: report cards began in
+November 2025, after the last legacy graded and ungraded inspections, and in
+Ofsted's 31 Aug 2026 data no school has a legacy visit newer than its report
+card, but the rule does not depend on that. Ties between G, U and RC on the same
+date resolve in the order report card, graded, ungraded.
+
+Invariants: `current_grade` is null or 1–4; `current_grade_date <=
+latest_visit_date`; `current_grade_basis` is null exactly when `current_grade`
+is null.
+
+### Expected results (Ofsted MI as at 31 Aug 2026)
+
+| URN | School | Ofsted data | Latest visit | Current grade |
+|---|---|---|---|---|
+| 102408 | Rabbsfarm Primary School | G 17 Jun 2025 Not judged; U 6 Feb 2020 remains Good | graded, 17 Jun 2025 | none |
+| 151783 | Acre Wood Academy | G 1 Oct 2024 Not judged; U 14 Mar 2023 remains Good (Concerns) | graded, 1 Oct 2024 | none |
+| 139888 | Washwood Heath Academy | G 3 Mar 2020 Good; U 21 May 2025 Standards maintained | ungraded, 21 May 2025, "Standards maintained" | Good, 3 Mar 2020, graded |
+| 104762 | Robins Lane Community Primary | G 7 Jan 2020 Good; U 18 Jul 2024 School remains Good | ungraded, 18 Jul 2024 | Good, 18 Jul 2024, confirmed |
+| 100094 | Royal Free Hospital Children's School | G 9 Oct 2019 Outstanding; U 5 Feb 2025 Some aspects not as strong | ungraded, 5 Feb 2025 | Outstanding, 9 Oct 2019, graded |
+| 136454 | Oakgrove School | U 13 Nov 2024 Standards maintained only | ungraded, 13 Nov 2024 | none |
+| 137086 | Bishop Stopford School | G 1 Apr 2025 Not judged | graded, 1 Apr 2025 | none |
+| 110048 | The Willink School | U 5 Oct 2023 remains Good; RC 6 May 2026 | report card, 6 May 2026 | none (report card shown) |
+| 149612 | St Michael's Catholic School | RC 10 Feb 2026 only | report card, 10 Feb 2026 | none (report card shown) |
+
+## What each page shows
+
+**Search and map badge** (`buildOfstedListBadge`), first match wins:
+
+1. Report card: "Report Card · *RC year*" (unchanged)
+2. Current grade: "*Grade* · *year of `current_grade_date`*"
+3. Latest visit: "Inspected · *year of `latest_visit_date`*"
+4. "Not yet inspected" (unchanged)
+
+**School page** (`OfstedSection`, both phases):
+
+- Title date: "Inspected *latest visit date*".
+- Headline: the report card; or the current grade with a source line
+  ("Graded inspection, 6 July 2016" or "Confirmed at an ungraded inspection,
+  14 March 2023"); or "No overall grade" with "Ofsted stopped giving overall
+  grades in September 2024".
+- "Latest visit" line when the latest visit is not the grade's source, e.g.
+  "Ungraded inspection, 13 Nov 2024: Standards maintained".
+- The area grid shows the graded inspection's judgements through
+  `ofstedLegacyAreas()`, dated by that inspection when it is not the latest
+  visit. The primary and secondary no-grade branches merge into one; the
+  secondary branch's four hard-coded areas (audit M2) go with it.
+
+**Compare:** `ofstedDisplay` returns `report_card`, `graded`, `confirmed`,
+`no_overall_grade` or `none`. The "Latest Ofsted inspection", "Result" and
+"Inspected" rows use the same fields as the school page.
+
+## Delivery
+
+Two pull requests. The mart columns exist before anything reads them, so
+neither needs compatibility code.
+
+### PR 1: pipeline (additive)
+
+- `stg_ofsted_inspections`: keep `graded_inspection_date`,
+  `ungraded_inspection_date` and `rc_inspection_date` as separate typed
+  columns, with the report-card date's existing guard. Keep `inspection_date`
+  (graded, else ungraded) for the current backend. Keep a row when any of the
+  three dates is present, so report-card-only schools are no longer dropped
+  (part of H3: 123 schools).
+- `int_ofsted_latest`: pick one row per URN by `latest_visit_date` descending,
+  then `rc_inspection_date`, `ungraded_inspection_date` and
+  `graded_inspection_date` descending (nulls last). A duplicate monthly row that
+  carries a newer report card therefore always wins. Add the five status
+  columns.
+- New mart `marts.fact_ofsted_latest`: one row per URN from `int_ofsted_latest`
+  with every column the pages need (status, area grades, report-card grades,
+  ungraded outcome, report URL). It does not join `dim_school`, so only the
+  monthly Ofsted DAG builds it.
+- `dim_school` is not changed in PR 1: the daily DAG does not rebuild
+  `int_ofsted_latest`, and reading a column that the monthly DAG has not yet
+  built would fail the daily run.
+- Visible effect: report-card-only schools gain their report card, because the
+  backend's existing reads of `fact_ofsted_inspection` now see their rows.
+  Nothing else changes.
+
+### PR 2: backend and UI (after the Ofsted DAG has run on PR 1)
+
+- `data_loader.py`: the list query and the batch query read
+  `marts.fact_ofsted_latest` instead of picking the latest row of
+  `fact_ofsted_inspection`. `_ofsted_block` reads the status columns and loses
+  its fallback to `ungraded_grade`.
+- List rows: `ofsted_grade` becomes `current_grade`; `ofsted_date` becomes
+  `latest_visit_date`; new `ofsted_grade_date`. `ofsted_rc_date` stays.
+- `ofsted` block: `overall_effectiveness` and `inspection_date` are the graded
+  inspection's own result and date (they label the area grid); new
+  `current_grade` `{grade, date, basis}` (or null) and `latest_visit`
+  `{date, kind, outcome}`; `grade_source` is removed. Report-card fields are
+  unchanged.
+- `dim_school.ofsted_grade` becomes `current_grade` (Typesense's rating follows
+  at the next sync); `ofsted_date` becomes `latest_visit_date`.
+- Sitemap: `lastmod` from `latest_visit_date`; `_PUBLISHABLE_FIELDS` also counts
+  a latest visit, so schools that lose a carried grade keep their sitemap entry.
+- Front end: `lib/types.ts`, `buildOfstedListBadge`, `OfstedSection`,
+  `PrimarySchoolSections`, `SecondarySchoolSections`, `compareLogic.ofstedDisplay`,
+  `CompareAtAGlance`, `CompareOfsted`. Place-page counts need no change.
+- Delete `buildOfstedHeroChip` and `buildSchoolSummary` in their own commit:
+  nothing renders them and they encode the old rule.
+
+## Testing
+
+**PR 1**
+
+- dbt unit tests on `int_ofsted_latest`, one per table row above plus
+  "report-card only" and "duplicate rows, newer report card wins".
+- Schema tests on `fact_ofsted_latest`: unique, not-null `urn`; accepted values
+  for `latest_visit_kind` and `current_grade_basis`; `current_grade` null or
+  1–4; `current_grade_date <= latest_visit_date`.
+- Run locally against a throwaway Postgres from `pgserver` (no Docker here). If
+  that fails, they still run in the Ofsted DAG's `dbt build`, which fails on any
+  broken case.
+- `pipeline/tests/test_dag_selectors.py` (PR #181) keeps passing.
+
+**PR 2**
+
+- pytest: contract test for the list and `ofsted` fields (style of
+  `test_school_page_flag_fields.py`); `_ofsted_block` from a
+  `fact_ofsted_latest` row; sitemap publishability.
+- Jest: a badge case per table row; `OfstedSection` for graded, confirmed, no
+  grade, the latest-visit line and a sixth-form area; `ofstedDisplay` kinds.
+  Rewrite tests that assert `carried_forward`.
+- E2E (same PR): Rabbsfarm's search row says "Inspected · 2025" and its page
+  says "No overall grade" with quality of education Requires Improvement; a
+  confirmed school says "Confirmed at an ungraded inspection". The existing
+  report-card journey stays.
+
+## Rollout and verification
+
+1. Merge PR 1. On staging, run `school_data_monthly_ofsted`, then:
+
+   ```sql
+   -- one row per school
+   select count(*) = count(distinct urn) from marts.fact_ofsted_latest;
+   -- the examples above
+   select urn, latest_visit_date, latest_visit_kind, latest_visit_outcome,
+          current_grade, current_grade_date, current_grade_basis
+   from marts.fact_ofsted_latest
+   where urn in (102408, 151783, 139888, 104762, 100094, 136454, 137086, 110048, 149612);
+   -- C1: a grade in force although the latest inspection gave none (expect 0)
+   select count(*) from marts.fact_ofsted_latest
+   where current_grade is not null and latest_visit_kind = 'graded'
+     and overall_effectiveness is null;
+   -- invariant (expect 0)
+   select count(*) from marts.fact_ofsted_latest where current_grade_date > latest_visit_date;
+   ```
+
+   Check through the API that St Michael's Catholic School (149612) shows its
+   report card.
+2. Promote PR 1 to production; run the Ofsted DAG there; repeat the checks.
+3. Merge PR 2. Let the daily DAG run (or trigger it) so `dim_school` and
+   Typesense pick up the change; run the E2E journeys; re-run the audit's C1,
+   M1 and M2 checks against staging: expect 0.
+4. Promote PR 2; repeat the audit checks on production.
+
+## Expected visible change
+
+About 932 schools change from a grade badge dated by a no-grade inspection
+("Good · 2025") to "Inspected · 2025". Counts of Good and Outstanding schools
+on place pages fall by the same schools, and Typesense's rating changes for
+them. Dates beside a grade can move earlier (to the inspection that awarded
+it); "Inspected" dates move later (to the latest visit).
+
+## Risks
+
+- Ofsted changes its MI columns most months. Unknown grade text parses to null
+  (`safe_numeric`), which degrades to "Inspected · year", never to a wrong grade.
+- PR 2 depends on the Ofsted DAG having run on the target environment after PR
+  1. If PR 2 is promoted first, the backend reads a missing table: promote in
+  order.

docs/superpowers/specs/2026-10-06-ks4-2023-24-and-la-averages-design.md

@@ -0,0 +1,300 @@
+# 2023/24 Results and DfE LA Averages — Design
+
+**Date:** 2026-10-06
+**Status:** approved design, not yet implemented
+**Scope:** `tap_uk_ees` (KS4 results, KS4 information, new LA stream),
+`safe_numeric`, new `fact_ks4_la_averages` mart, annual EES DAG selector,
+`/api/la-averages`, secondary search rows and map cards
+**Fixes:** audit findings C2 and H2, from the 3 Oct 2026 accuracy audit
+
+## Goal
+
+Show every 2023/24 result and school-information figure DfE published, and
+compare each state-funded secondary school with DfE's own local-authority
+average.
+
+## The problem
+
+### C2: 2023/24 is empty
+
+Bishop Stopford School (137086) shows Attainment 8 60.7 for 2022/23, nothing
+for 2023/24 and 58.7 for 2024/25. DfE's 2023/24 figures are Attainment 8 64.1,
+Progress 8 +1.02 and English and maths grade 4+ 91.7%. 2023/24 is the last year
+DfE published Progress 8 (2024/25 has no KS2 baseline), so the site shows no
+recent Progress 8 for any school. Site-wide, 4,170 listed schools have a DfE
+2023/24 Attainment 8 and 3,384 a Progress 8.
+
+There are three separate causes.
+
+1. **KS4 results.** The 2024/25 release's
+   `202425_performance_tables_schools_final.csv` is a time series: it holds
+   2022/23, 2023/24 and 2024/25 under the current column names, with the right
+   values (Bishop Stopford 2023/24: 64.1, 1.02, 91.7). The 2023/24 release's own
+   `202324_performance_tables_schools_final.csv`, re-issued on 10 March 2026,
+   uses the older names (`t_pupils`, `avg_att8`, `avg_p8score`,
+   `pt_l2basics_94` …). `EESDatasetStream` reads releases in the API's order,
+   newest first, so the old file is read last. Its rows carry none of the
+   declared fields, and target-postgres upserts on the stream's primary key
+   (`append_only = not key_properties` in meltanolabs-target-postgres 0.8.0),
+   so they overwrite the good 2023/24 rows with nulls.
+
+   The two files share the keys of every "Total" row, but 34,254 of the 57,090
+   2023/24 sub-group rows use different labels ("Low prior" against "Low prior
+   attainment"). Those old-label rows sit in `raw.ees_ks4_performance` with
+   null measures. Nothing reads them.
+
+2. **KS4 school information.** 2023/24 information exists only in the 2023/24
+   release, in `202324_information_about_schools_final.csv`, with the older
+   names. `EESKS4InfoStream` declares the newer ones, so prior attainment,
+   SEN percentages, disadvantage gaps and Progress 8 banding are null for
+   2023/24.
+
+3. **KS2 school information.** The 2023/24 file
+   `ks2_school_information_data.csv` uses the declared names, and pupil counts
+   load (school 147411: 818 pupils, 112 eligible). Its percentages are written
+   with a sign (`ptfsm6cla1a = "34%"`). `safe_numeric` accepts only
+   `^-?[0-9]+(\.[0-9]+)?$`, so disadvantaged, EAL, SEN and mobility percentages
+   are null for every school in 2023/24.
+
+DfE published no school-level KS2 information file for 2022/23 (the 2023/24
+release's attainment file carries 2022/23 attainment rows only). Those nulls are
+a gap in the source, not a defect.
+
+### H2: "vs LA avg" uses the wrong average
+
+`/api/la-averages` (`backend/app.py`) takes an unweighted mean of every school
+in the LA with an Attainment 8 score, independent and special schools included.
+Independent schools score low because DfE measures exclude IGCSEs, and special
+schools score low for other reasons, so the average is too low almost
+everywhere. Kensington and Chelsea's "LA avg" is 35.2: the mean of 6 state
+schools (54.9) and 8 independent schools (20.4). DfE's figure is 54.5. Of the
+151 LAs the audit compared, ours was lower in 147, by 7.1 points on average and
+by up to 19.3, so most secondary schools look better than their area.
+
+DfE's LA averages are already in the file the pipeline downloads for the
+England averages: the "summary, all state-funded" data set
+(`data-catalogue/data-set/1b649e16-01e8-435b-a814-56be2faf9054/csv`). Its
+`Local authority` / `All state-funded` / Total rows match DfE's published
+performance-table LA averages (RECTYPE 4) for all 152 LAs in 2024/25, with no
+difference. `EESKs4NationalStream` keeps the England row and discards them.
+"All state-funded" is the same population as the England benchmark the site
+already shows.
+
+Computing the average ourselves from state-funded schools, weighted by pupils,
+was tested and rejected: it differs from DfE's figure by 1.1 points on average
+and is never exact.
+
+## Non-goals
+
+- 2022/23 KS2 school information (DfE published none).
+- An "excludes IGCSEs" note wherever an independent school's Attainment 8
+  appears. This change only stops comparing independent schools with the LA.
+- Showing 2023/24 Progress 8 in the GCSE section's headline. The history section
+  shows it once the data loads; the 2024/25 banner stays true.
+- Updating the fixed EES data-set id when DfE publishes 2025/26. It already
+  feeds the England averages; the LA stream shares it.
+- LA comparisons for other measures or on other pages.
+- Deleting the leftover old-label raw rows automatically.
+
+## The rules
+
+### The newest release owns every year it contains (KS4 results only)
+
+`EESDatasetStream` gets an opt-in class attribute,
+`_newest_release_owns_period: bool = False`. `EESKS4PerformanceStream` sets it
+to `True`. When it is on:
+
+- releases are processed newest first by `time_period` (from the release slug),
+  not in the API's order;
+- the stream records each `time_period` it has emitted;
+- in each older release, rows whose `time_period` a newer release already
+  emitted are dropped, and the stream logs how many it skipped and for which
+  years;
+- years only an older release contains are emitted as before.
+
+The filter is a pure function, testable without a download. Other streams keep
+the current behaviour. A general rule would be wrong: the 2024/25 KS2 file holds
+98,448 of the 955,956 rows the 2023/24 release has for 2023/24.
+
+### KS4 information: old names
+
+`EESKS4InfoStream._column_renames` maps the 2023/24 names onto the declared
+fields:
+
+| 2023/24 column | Declared field |
+|---|---|
+| `t_allks_pupils` | `allks_pupil_count` |
+| `t_allks_boys` | `allks_boys_count` |
+| `t_allks_girls` | `allks_girls_count` |
+| `t_pupils` | `endks4_pupil_count` |
+| `avg_ks2_scaledscore` | `ks2_scaledscore_average` |
+| `pt_sen_with_ehcp` | `sen_with_ehcp_pupil_percent` |
+| `pt_sen` | `sen_pupil_percent` |
+| `pt_sen_no_ehcp` | `sen_no_ehcp_pupil_percent` |
+| `diffn_att8` | `attainment8_diffn` |
+| `diffn_p8mea` | `progress8_diffn` |
+| `p8_banding` | `progress8_banding` |
+
+Newer files contain none of the old names, so they are unaffected.
+
+### `safe_numeric` accepts a trailing `%`
+
+The pattern becomes `^-?[0-9]+(\.[0-9]+)?%?$` and the cast reads
+`rtrim(col, '%')`. A value such as `34%` can only mean 34. Suppression codes
+(`c`, `z`, `x` …) still become null.
+
+### LA averages
+
+A new stream, `ees_ks4_la`, reads the same CSV as `ees_ks4_national` and keeps
+rows where `geographic_level = 'Local authority'`,
+`establishment_type_group = 'All state-funded'`, `breakdown_topic = 'Total'` and
+`breakdown = 'Total'` (case-insensitive, as the national stream compares). It
+emits `time_period`, `old_la_code`, `new_la_code`, `la_name` and the 8 headline
+measures the national stream emits (`_KS4_NATIONAL_COL_MAP`). Primary key:
+(`time_period`, `old_la_code`). The two streams share one download-and-filter
+helper.
+
+`old_la_code` is the GIAS LA code (`local_authority_code`), so schools join on
+the code, not the name. Names match today for every LA DfE publishes; DfE
+publishes no figure for City of London.
+
+### Which schools get a gap
+
+The search row and the map card show "vs LA avg" only when the school has an
+Attainment 8 score, is neither special (`isSpecialSchool`) nor independent
+(`isIndependentSchool`: "independent" in the GIAS type, which covers "Other
+independent school" and "Other independent special school"), and its LA has a
+DfE figure for the year the endpoint serves.
+
+## Delivery
+
+Two PRs, as for C1.
+
+### PR 1: pipeline
+
+- `pipeline/plugins/extractors/tap-uk-ees/tap_uk_ees/tap.py`: release
+  precedence, KS4 information renames, `ees_ks4_la` stream registered in
+  `discover_streams`, shared national/LA helper.
+- `pipeline/transform/macros/safe_numeric.sql`: trailing `%`.
+- `pipeline/transform/models/staging/`: source `raw.ees_ks4_la` and
+  `stg_ees_ks4_la` (view): `cast(old_la_code as integer) as la_code`,
+  `cast(time_period as integer) as year`, `la_name`, measures via
+  `safe_numeric`, named as in `stg_ees_ks4_national`.
+- `pipeline/transform/models/marts/fact_ks4_la_averages.sql` (table): one row
+  per (`year`, `la_code`) with `la_name` and the columns of
+  `fact_ks4_national_averages`. Schema tests: unique (`year`, `la_code`);
+  `year`, `la_code` and `la_name` not null.
+- Data tests in `pipeline/transform/tests/`:
+  - `assert_ks4_years_have_results`: every year in `stg_ees_ks4` has a non-null
+    Attainment 8 for at least 50% of its rows. DfE's files reach 82% each year;
+    2023/24 loads at 0% today. Pre-2019 years come from the legacy model and are
+    not tested.
+  - `assert_ks2_info_percentages_loaded`: for every year in `stg_ees_ks2` where
+    at least 1,000 rows have `total_pupils`, at least 90% of those rows have
+    `disadvantaged_pct`. DfE's files reach 96–97%. 2022/23 has no pupil counts
+    and is skipped.
+  - `assert_ks4_la_averages_cover_las`: the latest year in
+    `fact_ks4_la_averages` has at least 145 LAs (DfE: 152).
+- `pipeline/dags/school_data_pipeline.py`: the annual EES build selects
+  `stg_ees_ks4_la+`.
+- `docs/ARCHITECTURE.md`: LA averages come from DfE's data set.
+
+### PR 2: backend and UI (after the EES DAG has run on PR 1)
+
+- `backend/models.py`: `Ks4LaAverage` for `marts.fact_ks4_la_averages`.
+- `backend/app.py` `/api/la-averages`: the year is the latest with any school
+  Attainment 8 (as now). It reads that year's rows from the mart and keys each
+  `attainment_8_score` by our LA name, through the `local_authority_code` →
+  `local_authority` pairs in the school data. The response shape is unchanged.
+  No rows for that year, a missing table or a query error give an empty map,
+  logged, never another year's figures and never a computed mean.
+- `nextjs-app/lib/utils.ts`: `isIndependentSchool(school)`.
+- `nextjs-app/components/SecondarySchoolRow.tsx` and
+  `nextjs-app/components/LeafletMapInner.tsx`: the rule in "Which schools get a
+  gap".
+- `e2e/tests/journeys.spec.ts`: the two journeys under Testing.
+
+## Testing
+
+**Extractor (pytest, `pipeline/tests/`, new):**
+
+- precedence: with the flag on, a year in a newer release is emitted once, from
+  the newer release; a year only an older release has is kept; with the flag
+  off, every row passes;
+- releases arriving oldest first are still processed newest first;
+- KS4 information: an old-format row yields `endks4_pupil_count`,
+  `ks2_scaledscore_average`, `progress8_banding` and the rest of the table;
+- LA filter: a small CSV with national, regional, LA and sub-group rows yields
+  one row per LA and year, with the declared fields.
+
+**dbt (local `pgserver`, as for C1):**
+
+- unit test on `stg_ees_ks2`: `34%` → 34, `34` → 34, `c` → null;
+- unit test on `stg_ees_ks4_la` or the mart: codes and years cast, measures
+  carried;
+- the three data tests and the schema tests above;
+- `pipeline/tests/test_dag_selectors.py` passes with the new selector.
+
+**Backend (pytest):**
+
+- the response gives the mart's figure where the fixture's plain mean differs;
+- matching works by code when the mart's `la_name` differs from ours;
+- a mart without the served year, and a missing table, give an empty map.
+
+**Front end (Jest):**
+
+- `isIndependentSchool` for "Other independent school", "Other independent
+  special school", "Academy converter" and null;
+- `SecondarySchoolRow` and the map card show no gap for an independent school
+  and show one for a state school with an LA figure.
+
+**E2E (`journeys.spec.ts`, PR 2):**
+
+- C2: Bishop Stopford (137086) history shows 2023/24 Attainment 8 64.1 and
+  Progress 8 +1.02. These are final figures, so the journey stays stable.
+- H2: a search returning an independent and a state secondary: the independent
+  row has no "vs LA avg", the state row has one. The exact gap is not asserted:
+  DfE's 2025/26 provisional KS4 data is due and would change it.
+
+## Rollout and verification
+
+1. PR 1 merges to staging. Tudor runs `school_data_annual_ees` on staging.
+2. Through the staging API: Bishop Stopford 2023/24 Attainment 8 64.1 and
+   Progress 8 1.02; school 147411 2023/24 disadvantaged 34; the LA mart has 152
+   LAs for 2024/25. If a data test fails, the build stops before search sync;
+   investigate before going further.
+3. PR 2 merges, so the post-merge E2E gate runs against loaded data.
+4. Production, Tudor's decision, in order: promote PR 1, run the EES DAG on
+   production, promote PR 2. If PR 2 arrives first, the endpoint returns an
+   empty map and rows show no gap, never a wrong one.
+5. Optional cleanup, in the PR 1 description for Tudor:
+   `delete from raw.ees_ks4_performance where time_period = '202324' and pupil_count is null`.
+   New-format rows always have `pupil_count` (suppressed values are `c` or `z`,
+   not null), so this removes exactly the old-label leftovers.
+6. Validation on production against DfE's files: every listed school's 2023/24
+   Attainment 8, Progress 8 and English and maths figures match; the 2023/24 KS4
+   and KS2 information fields match; `/api/la-averages` equals DfE for all 152
+   LAs; independent rows show no gap. Then mark C2 and H2 resolved in the audit
+   report.
+
+## Expected visible change
+
+- Secondary history charts and tables run unbroken from 2022/23 to 2024/25, and
+  2023/24 Progress 8 appears for about 3,400 schools.
+- 2023/24 school information (KS2 and KS4) fills in.
+- "vs LA avg" drops for most state secondaries. In Kensington and Chelsea, a
+  school with Attainment 8 60.0 moves from +24.8 to +5.5.
+- Independent schools and City of London schools show no LA gap.
+
+## Risks
+
+- **Data-test thresholds stop a good build.** They were set from DfE's own
+  files (82% and 96–97% against 50% and 90%). A failure means the data changed
+  shape, which is what they are for.
+- **`safe_numeric` is shared by 14 models.** Values written as `n%` were null
+  and become numbers. No DfE column uses `%` for anything but a percentage.
+  The staging EES run is the check.
+- **Precedence drops data an older release holds more completely.** It is
+  opt-in for KS4 results, where both files hold the same 57,090 2023/24 keys.
+- **The fixed EES data-set id goes stale** when 2025/26 is published. The
+  endpoint's year check then gives no gap rather than a mismatched one.

e2e/tests/journeys.spec.ts

@@ -410,6 +410,29 @@ test('search and the school page agree on how many pupils a secondary has', asyn
   expect(school.total_pupils).toBe(detail.school_info.total_pupils);
 });
 
+test('a secondary search row compares its Attainment 8 with the LA average', async ({ page }) => {
+  // The comparison vanished unnoticed: the averages were fetched with
+  // force-cache, so one stored failure hid it in that browser for good.
+  // Playwright disables the HTTP cache when it intercepts requests, so this
+  // guards the comparison itself; the unit test pins the cache mode.
+  const la = await (await page.request.get('/api/la-averages')).json();
+  const averages: Record<string, number> = la.secondary?.attainment_8_by_la ?? {};
+  const res = await page.request.get('/api/schools?search=school&phase=secondary&page_size=50');
+  expect(res.ok()).toBeTruthy();
+  const school = ((await res.json()).schools ?? []).find(
+    (s: { attainment_8_score?: number | null; local_authority?: string; school_type?: string }) =>
+      s.attainment_8_score != null && s.local_authority != null && averages[s.local_authority] != null
+      && !/special|pupil referral|alternative provision/i.test(s.school_type ?? ''));
+  test.skip(!school, 'no mainstream secondary with an LA average here');
+
+  await searchByName(page, school.school_name);
+  const link = page.locator(`a[href^="/school/${school.urn}-"]`).first();
+  await expect(link).toBeVisible({ timeout: 15_000 });
+  const stats = link.locator('xpath=ancestor::div[contains(@class, "__rowContent")][1]')
+    .locator('[class*="__line3"]');
+  await expect(stats.getByText(/vs LA avg/)).toBeVisible();
+});
+
 test('a phase outside primary/secondary filters to that phase, not to everything', async ({ page }) => {
   // The search page offers every GIAS phase, but the API only knew the grouped
   // ones and silently dropped the rest — so "Nursery" returned primaries.
@@ -451,6 +474,37 @@ test('a report-card school shows a Report Card badge in search results, not its
   await expect(page.getByText(/Report Card ·/).first()).toBeVisible();
 });
 
+test('a school whose latest inspection gave no grade is not shown with an older grade', async ({ page }) => {
+  // Rabbsfarm (102408): Ofsted's 17 June 2025 inspection gave no overall
+  // grade and rated three areas Requires Improvement. The site used to carry
+  // a 2020 "remains Good" forward and print "Good · 2025" (audit C1).
+  const URN = 102408;
+  const res = await page.request.get(`/api/schools/${URN}`);
+  expect(res.ok()).toBeTruthy();
+  const ofsted = (await res.json()).ofsted;
+  expect(ofsted.current_grade).toBeNull();
+  expect(ofsted.latest_visit.date).toBe('2025-06-17');
+
+  await searchByName(page, 'Rabbsfarm Primary');
+  const row = page.locator(`a[href*="${URN}"]`).first();
+  await expect(row).toBeVisible({ timeout: 15_000 });
+  await expect(page.getByText('Inspected · 2025').first()).toBeVisible();
+  await expect(page.getByText(/Good · 2025/)).toHaveCount(0);
+
+  await page.goto(`/school/${URN}`);
+  const section = page.locator('#ofsted');
+  await expect(section.getByText('No overall grade')).toBeVisible();
+  await expect(section.getByText('Requires Improvement').first()).toBeVisible();
+});
+
+test('a grade confirmed at an ungraded visit says so and is dated by it', async ({ page }) => {
+  const URN = 104762; // Robins Lane: graded Good Jan 2020, "School remains Good" 18 July 2024
+  await page.goto(`/school/${URN}`);
+  const section = page.locator('#ofsted');
+  await expect(section).toBeVisible({ timeout: 15_000 });
+  await expect(section.getByText('Confirmed at an ungraded inspection, 18 July 2024')).toBeVisible();
+});
+
 test('school detail page renders name and performance data', async ({ page }) => {
   await searchByName(page, 'primary');
   const firstSchool = schoolLinks(page).first();

nextjs-app/__tests__/components/CompareOfsted.test.tsx

@@ -33,18 +33,26 @@ function ofsted(partial: Partial<OfstedInspection>): OfstedInspection {
   };
 }
 
-const schools = [school(1, 'Graded School'), school(2, 'Carried School'), school(3, 'Card School')];
+const schools = [school(1, 'Graded School'), school(2, 'Confirmed School'), school(3, 'Card School')];
 
 const data: Record<string, ComparisonData> = {
   '1': {
     school_info: schools[0],
     yearly_data: [],
-    ofsted: ofsted({ overall_effectiveness: 1, grade_source: 'graded' }),
+    ofsted: ofsted({
+      overall_effectiveness: 1,
+      current_grade: { grade: 1, date: '2021-10-07', basis: 'graded' },
+      latest_visit: { date: '2021-10-07', kind: 'graded', outcome: null },
+    }),
   },
   '2': {
     school_info: schools[1],
     yearly_data: [],
-    ofsted: ofsted({ overall_effectiveness: 2, grade_source: 'ungraded_carried_forward' }),
+    ofsted: ofsted({
+      overall_effectiveness: 2,
+      current_grade: { grade: 2, date: '2023-03-14', basis: 'confirmed' },
+      latest_visit: { date: '2023-03-14', kind: 'ungraded', outcome: 'School remains Good' },
+    }),
   },
   '3': {
     school_info: schools[2],
@@ -65,9 +73,9 @@ describe('CompareOfsted', () => {
     render(<CompareOfsted schools={schools} data={data} />);
 
     expect(screen.getByText('Outstanding')).toBeInTheDocument();
-    // Carried-forward grade is shown but marked as such
+    // A grade confirmed at an ungraded visit says so, with that visit's date
     expect(screen.getByText('Good')).toBeInTheDocument();
-    expect(screen.getByText(/carried forward/i)).toBeInTheDocument();
+    expect(screen.getByText('Confirmed at an ungraded inspection, 14 March 2023')).toBeInTheDocument();
     // Report card: label present, no overall-grade badge for that school
     expect(screen.getByText('Report card')).toBeInTheDocument();
     expect(screen.getByText(/no overall grade/i)).toBeInTheDocument();
@@ -104,7 +112,7 @@ describe('CompareOfsted', () => {
         yearly_data: [],
         ofsted: ofsted({
           overall_effectiveness: 2,
-          grade_source: 'graded',
+          current_grade: { grade: 2, date: '2021-10-07', basis: 'graded' },
           quality_of_education: 1,
           early_years_provision: 9,
           sixth_form_provision: 2,
@@ -167,4 +175,26 @@ describe('CompareOfsted', () => {
     expect(screen.getAllByText('Graded').length).toBe(4);
     expect(screen.getAllByText('Card').length).toBe(4);
   });
+
+  it('dates "Inspected" by the latest visit, not the graded inspection (Washwood Heath)', () => {
+    const s1 = school(7, 'Washwood Heath Academy');
+    render(<CompareOfsted schools={[s1]} data={{ '7': { school_info: s1, yearly_data: [], ofsted: ofsted({
+      inspection_date: '2020-03-03', overall_effectiveness: 2, quality_of_education: 2,
+      current_grade: { grade: 2, date: '2020-03-03', basis: 'graded' },
+      latest_visit: { date: '2025-05-21', kind: 'ungraded', outcome: 'Standards maintained' },
+    }) } }} />);
+    expect(screen.getByText(/21 May 2025/)).toBeInTheDocument();
+    expect(screen.queryByText('4+ years ago')).not.toBeInTheDocument();
+    expect(screen.getByText('Graded inspection, 3 March 2020')).toBeInTheDocument();
+  });
+
+  it('shows no overall grade after a no-grade inspection (Rabbsfarm)', () => {
+    const s1 = school(8, 'Rabbsfarm Primary School');
+    render(<CompareOfsted schools={[s1]} data={{ '8': { school_info: s1, yearly_data: [], ofsted: ofsted({
+      inspection_date: '2025-06-17', quality_of_education: 3,
+      current_grade: null, latest_visit: { date: '2025-06-17', kind: 'graded', outcome: null },
+    }) } }} />);
+    expect(screen.getAllByText('No overall grade').length).toBeGreaterThan(0);
+    expect(screen.queryByText('Good')).not.toBeInTheDocument();
+  });
 });

nextjs-app/__tests__/components/HomeView.staleFetch.test.tsx

@@ -1,6 +1,6 @@
 import { act, fireEvent, render, screen } from '@testing-library/react';
 import { HomeView } from '@/components/HomeView';
-import { fetchSchools } from '@/lib/api';
+import { fetchLAaverages, fetchSchools } from '@/lib/api';
 import { primaryFixture } from '../support/schoolFixtures';
 import type { SchoolsResponse, School } from '@/lib/types';
 
@@ -84,3 +84,23 @@ test('failed map requests can be retried by reopening the map', async () => {
   expect(fetchSchools).toHaveBeenCalledTimes(2);
   expect(screen.getByTestId('map')).toHaveTextContent('Retry result');
 });
+
+test('LA averages are not fetched with force-cache, so one failure is not replayed for good', async () => {
+  // force-cache serves any stored response, however old, without asking the
+  // server. A request that failed once (a staging deploy restart, the July
+  // proxy outage) was stored and replayed on every later visit, and the
+  // "vs LA avg" delta vanished from every secondary row in that browser.
+  // The default mode honours the API's Cache-Control and never reuses an
+  // error.
+  params = new URLSearchParams('search=high');
+  const secondary: SchoolsResponse = {
+    ...response('Alpha High'),
+    schools: [{ ...primaryFixture.schoolInfo, school_name: 'Alpha High', phase: 'Secondary', attainment_8_score: 50 }],
+  };
+  render(<HomeView initialSchools={secondary} filters={filters} />);
+  await act(async () => {});
+  expect(fetchLAaverages).toHaveBeenCalled();
+  for (const [options] of jest.mocked(fetchLAaverages).mock.calls) {
+    expect(options?.cache).not.toBe('force-cache');
+  }
+});

nextjs-app/__tests__/components/NearbySchoolsSection.test.tsx

@@ -8,7 +8,6 @@
 import { render, screen } from '@testing-library/react';
 
 import {
-  nearbyNoun,
   NearbySchoolsSection,
   shouldRenderNearby,
 } from '@/components/school/NearbySchoolsSection';
@@ -43,13 +42,7 @@ function school(overrides: Partial<NearbySchool> = {}): NearbySchool {
 
 function renderSection(nearby: NearbySchool[]) {
   return render(
-    <NearbySchoolsSection
-      urn={100001}
-      schoolName="Meadowbrook Primary School"
-      phase="Primary"
-      thisMetricValue={72}
-      nearby={nearby}
-    />,
+    <NearbySchoolsSection urn={100001} thisMetricValue={72} nearby={nearby} />,
   );
 }
 
@@ -90,15 +83,10 @@ describe('what the section claims', () => {
   });
 
   it('shows no chips at all when nothing is shared, rather than inventing one', () => {
-    const { container } = render(
-      <NearbySchoolsSection
-        urn={100001}
-        schoolName="Meadowbrook Primary School"
-        phase="Primary"
-        thisMetricValue={72}
-        nearby={[school({ shared: [] }), school({ urn: 100003, shared: [] })]}
-      />,
-    );
+    const { container } = renderSection([
+      school({ shared: [] }),
+      school({ urn: 100003, shared: [] }),
+    ]);
     // The card still carries its distance, name, type and figure — just no
     // claim of likeness.
     expect(container.querySelectorAll('li ul').length).toBe(0);
@@ -106,37 +94,6 @@ describe('what the section claims', () => {
   });
 });
 
-describe('what the lede calls the set', () => {
-  it.each([
-    ['Primary', 'primary schools'],
-    ['Middle deemed primary', 'primary schools'],
-    ['Secondary', 'secondary schools'],
-    ['Middle deemed secondary', 'secondary schools'],
-    ['All-through', 'all-through schools'],
-    // GIAS phase 6. Its candidates span the whole secondary group, so no
-    // single noun fits and it takes the honest general one.
-    ['16 plus', 'schools and colleges'],
-    ['', 'schools'],
-    [null, 'schools'],
-  ])('calls a %s school\'s neighbours "%s"', (phase, expected) => {
-    expect(nearbyNoun(phase)).toBe(expected);
-  });
-
-  it('never calls a sixth form college\'s neighbours primary schools', () => {
-    render(
-      <NearbySchoolsSection
-        urn={100001}
-        schoolName="Barnet Sixth Form College"
-        phase="16 plus"
-        thisMetricValue={null}
-        nearby={[school(), school({ urn: 100003 })]}
-      />,
-    );
-    expect(screen.getByText(/Other schools and colleges near Barnet Sixth Form College/)).toBeInTheDocument();
-    expect(screen.queryByText(/primary schools/)).not.toBeInTheDocument();
-  });
-});
-
 describe('cards', () => {
   it('links each school to its canonical slug', () => {
     renderSection([school(), school({ urn: 100003, school_name: 'Oakfield Primary School' })]);

nextjs-app/__tests__/components/OfstedSection.test.tsx

@@ -0,0 +1,84 @@
+import { render, screen } from '@testing-library/react';
+import { OfstedSection } from '@/components/school/OfstedSection';
+import { ofstedLegacyAreas } from '@/lib/utils';
+import type { OfstedInspection } from '@/lib/types';
+
+const empty = {
+  framework: null, inspection_date: null, inspection_type: null, overall_effectiveness: null,
+  quality_of_education: null, behaviour_attitudes: null, personal_development: null,
+  leadership_management: null, early_years_provision: null, sixth_form_provision: null,
+  previous_overall: null, rc_safeguarding_met: null, rc_inclusion: null, rc_curriculum_teaching: null,
+  rc_achievement: null, rc_attendance_behaviour: null, rc_personal_development: null,
+  rc_leadership_governance: null, rc_early_years: null, rc_sixth_form: null, report_url: null,
+  report_card: {},
+} as OfstedInspection;
+
+// `page` mimics how each school page used to mount the section; the secondary
+// page's branch hard-coded four areas and dropped the sixth form (audit M2).
+function renderSection(o: Partial<OfstedInspection>, page: Record<string, unknown> = {}) {
+  const ofsted = { ...empty, ...o } as OfstedInspection;
+  render(
+    <OfstedSection
+      {...page}
+      ofsted={ofsted}
+      urn={1}
+      isReportCard={false}
+      ofstedInspectedDate={ofsted.latest_visit?.date ?? null}
+      oeifAllSameGrade={false}
+      oeifAreas={ofstedLegacyAreas(ofsted)}
+    />,
+  );
+}
+
+it('shows no overall grade, not an older one, after a no-grade inspection (Rabbsfarm)', () => {
+  renderSection({
+    inspection_date: '2025-06-17', quality_of_education: 3, behaviour_attitudes: 3,
+    personal_development: 2, leadership_management: 3, early_years_provision: 2,
+    current_grade: null, latest_visit: { date: '2025-06-17', kind: 'graded', outcome: null },
+  });
+  expect(screen.getByText(/Inspected 17 June 2025/)).toBeInTheDocument();
+  expect(screen.getByText('No overall grade')).toBeInTheDocument();
+  expect(screen.queryByText('Good', { selector: 'span' })).not.toBeInTheDocument();
+  expect(screen.queryByText('Not rated')).not.toBeInTheDocument();
+  expect(screen.getAllByText('Requires Improvement')).toHaveLength(3);
+});
+
+it('keeps the sixth-form judgement when there is no overall grade (audit M2)', () => {
+  renderSection({
+    inspection_date: '2025-04-01', quality_of_education: 1, behaviour_attitudes: 1,
+    personal_development: 1, leadership_management: 1, sixth_form_provision: 2,
+    current_grade: null, latest_visit: { date: '2025-04-01', kind: 'graded', outcome: null },
+  }, { variant: 'secondary' });
+  expect(screen.getByText(/sixth form/i)).toBeInTheDocument();
+  expect(screen.getByText('Good')).toBeInTheDocument();
+});
+
+it('dates a grade by its source and prints a later visit separately (Washwood Heath)', () => {
+  renderSection({
+    inspection_date: '2020-03-03', overall_effectiveness: 2, quality_of_education: 2,
+    current_grade: { grade: 2, date: '2020-03-03', basis: 'graded' },
+    latest_visit: { date: '2025-05-21', kind: 'ungraded', outcome: 'Standards maintained' },
+  });
+  expect(screen.getByText(/Inspected 21 May 2025/)).toBeInTheDocument();
+  expect(screen.getByText('Graded inspection, 3 March 2020')).toBeInTheDocument();
+  expect(screen.getByText(/Latest visit: Ungraded inspection, 21 May 2025: Standards maintained/)).toBeInTheDocument();
+});
+
+it('says a grade was confirmed at an ungraded visit (Robins Lane)', () => {
+  renderSection({
+    inspection_date: '2020-01-07', overall_effectiveness: 2,
+    current_grade: { grade: 2, date: '2024-07-18', basis: 'confirmed' },
+    latest_visit: { date: '2024-07-18', kind: 'ungraded', outcome: 'School remains Good' },
+  });
+  expect(screen.getByText('Confirmed at an ungraded inspection, 18 July 2024')).toBeInTheDocument();
+  expect(screen.queryByText(/Latest visit/)).not.toBeInTheDocument();
+});
+
+it('prints an ungraded outcome when there is no grade (Oakgrove)', () => {
+  renderSection({
+    current_grade: null,
+    latest_visit: { date: '2024-11-13', kind: 'ungraded', outcome: 'Standards maintained' },
+  });
+  expect(screen.getByText('No overall grade')).toBeInTheDocument();
+  expect(screen.getByText(/Ungraded inspection, 13 November 2024: Standards maintained/)).toBeInTheDocument();
+});

nextjs-app/__tests__/lib/compareLogic.test.ts

@@ -114,16 +114,13 @@ describe('ofstedDisplay', () => {
     expect(d.kind).toBe('report_card');
   });
 
-  it('distinguishes graded from carried-forward grades', () => {
-    const graded = ofstedDisplay(
-      ofsted({ overall_effectiveness: 1, grade_source: 'graded' }),
-    );
-    expect(graded).toMatchObject({ kind: 'graded', gradeLabel: 'Outstanding', carriedForward: false });
-
-    const carried = ofstedDisplay(
-      ofsted({ overall_effectiveness: 2, grade_source: 'ungraded_carried_forward' }),
-    );
-    expect(carried).toMatchObject({ kind: 'carried_forward', gradeLabel: 'Good', carriedForward: true });
+  it('distinguishes a graded grade from a confirmed one', () => {
+    expect(ofstedDisplay(ofsted({ current_grade: { grade: 1, date: '2019-10-09', basis: 'graded' },
+      latest_visit: { date: '2025-02-05', kind: 'ungraded', outcome: 'Some aspects not as strong' } })))
+      .toMatchObject({ kind: 'graded', gradeLabel: 'Outstanding', gradeDate: '2019-10-09' });
+    expect(ofstedDisplay(ofsted({ current_grade: { grade: 2, date: '2024-07-18', basis: 'confirmed' },
+      latest_visit: { date: '2024-07-18', kind: 'ungraded', outcome: 'School remains Good' } })))
+      .toMatchObject({ kind: 'confirmed', gradeLabel: 'Good' });
   });
 
   it('handles missing data', () => {
@@ -131,11 +128,11 @@ describe('ofstedDisplay', () => {
     expect(ofstedDisplay(ofsted({})).kind).toBe('none');
   });
 
-  it('identifies transitional inspections without overall grades', () => {
-    const transitional = ofstedDisplay(
-      ofsted({ overall_effectiveness: null, inspection_date: '2024-11-05' }),
-    );
-    expect(transitional.kind).toBe('transitional');
+  it('has no overall grade when the latest inspection gave none', () => {
+    // Rabbsfarm: the graded inspection's own overall is null, so no grade is
+    // in force even though an older ungraded visit said "remains Good".
+    expect(ofstedDisplay(ofsted({ current_grade: null, overall_effectiveness: null,
+      latest_visit: { date: '2025-06-17', kind: 'graded', outcome: null } })).kind).toBe('no_overall_grade');
   });
 
   it('uses the four legacy grade words', () => {

nextjs-app/__tests__/lib/ofstedStatus.test.ts

@@ -0,0 +1,47 @@
+import { gradeSourceLine, latestVisitLine, showLatestVisitLine } from '@/lib/ofstedStatus';
+import type { OfstedInspection } from '@/lib/types';
+
+const base = { report_card: {} } as unknown as OfstedInspection;
+
+describe('gradeSourceLine', () => {
+  it('names the graded inspection and its date', () => {
+    expect(gradeSourceLine({ grade: 2, date: '2016-07-06', basis: 'graded' }))
+      .toBe('Graded inspection, 6 July 2016');
+  });
+  it('names the ungraded visit that confirmed it', () => {
+    expect(gradeSourceLine({ grade: 2, date: '2023-03-14', basis: 'confirmed' }))
+      .toBe('Confirmed at an ungraded inspection, 14 March 2023');
+  });
+});
+
+describe('latestVisitLine', () => {
+  it('prints the ungraded outcome', () => {
+    expect(latestVisitLine({ date: '2024-11-13', kind: 'ungraded', outcome: 'Standards maintained' }))
+      .toBe('Ungraded inspection, 13 November 2024: Standards maintained');
+  });
+  it('prints a graded visit without an outcome', () => {
+    expect(latestVisitLine({ date: '2025-06-17', kind: 'graded', outcome: null }))
+      .toBe('Graded inspection, 17 June 2025');
+  });
+});
+
+describe('showLatestVisitLine', () => {
+  it('shows a later visit than the one the grade came from', () => {
+    expect(showLatestVisitLine({ ...base,
+      current_grade: { grade: 2, date: '2020-03-03', basis: 'graded' },
+      latest_visit: { date: '2025-05-21', kind: 'ungraded', outcome: 'Standards maintained' } })).toBe(true);
+  });
+  it('hides it when the visit is the grade’s own source', () => {
+    expect(showLatestVisitLine({ ...base,
+      current_grade: { grade: 2, date: '2024-07-18', basis: 'confirmed' },
+      latest_visit: { date: '2024-07-18', kind: 'ungraded', outcome: 'School remains Good' } })).toBe(false);
+  });
+  it('shows an ungraded outcome when there is no grade', () => {
+    expect(showLatestVisitLine({ ...base, current_grade: null,
+      latest_visit: { date: '2024-11-13', kind: 'ungraded', outcome: 'Standards maintained' } })).toBe(true);
+  });
+  it('hides it for a graded visit with no grade (the title already dates it)', () => {
+    expect(showLatestVisitLine({ ...base, current_grade: null,
+      latest_visit: { date: '2025-06-17', kind: 'graded', outcome: null } })).toBe(false);
+  });
+});

nextjs-app/__tests__/lib/utils.test.ts

@@ -147,23 +147,37 @@ describe('ofstedLegacyAreas', () => {
 
 describe('buildOfstedListBadge', () => {
   it('returns grade word + year for OEIF Outstanding', () => {
-    const badge = buildOfstedListBadge({ ofsted_grade: 1, ofsted_date: '2023-11-15', ofsted_framework: 'OEIF' });
+    const badge = buildOfstedListBadge({ ofsted_grade: 1, ofsted_grade_date: '2023-11-15', ofsted_date: '2023-11-15', ofsted_framework: 'OEIF' });
     expect(badge.label).toBe('Outstanding · 2023');
     expect(badge.cssClass).toBe('ofsted1');
   });
 
   it('returns grade word for each OEIF grade', () => {
-    expect(buildOfstedListBadge({ ofsted_grade: 2, ofsted_date: '2022-05-01' }).label).toBe('Good · 2022');
-    expect(buildOfstedListBadge({ ofsted_grade: 3, ofsted_date: '2021-01-01' }).label).toBe('Req. Improvement · 2021');
-    expect(buildOfstedListBadge({ ofsted_grade: 4, ofsted_date: '2020-03-01' }).label).toBe('Inadequate · 2020');
+    expect(buildOfstedListBadge({ ofsted_grade: 2, ofsted_grade_date: '2022-05-01' }).label).toBe('Good · 2022');
+    expect(buildOfstedListBadge({ ofsted_grade: 3, ofsted_grade_date: '2021-01-01' }).label).toBe('Req. Improvement · 2021');
+    expect(buildOfstedListBadge({ ofsted_grade: 4, ofsted_grade_date: '2020-03-01' }).label).toBe('Inadequate · 2020');
   });
 
-  it('returns grade word without year when date is missing', () => {
-    const badge = buildOfstedListBadge({ ofsted_grade: 2, ofsted_date: null });
+  it('prints a grade without a year when its date is missing', () => {
+    const badge = buildOfstedListBadge({ ofsted_grade: 2, ofsted_grade_date: null, ofsted_date: '2025-01-01' });
     expect(badge.label).toBe('Good');
     expect(badge.cssClass).toBe('ofsted2');
   });
 
+  it('dates a grade by the inspection that awarded it, not the latest visit', () => {
+    // Washwood Heath: Good from a March 2020 graded inspection; latest visit
+    // an ungraded one in May 2025 (audit M1).
+    const badge = buildOfstedListBadge({ ofsted_grade: 2, ofsted_grade_date: '2020-03-03', ofsted_date: '2025-05-21' });
+    expect(badge.label).toBe('Good · 2020');
+  });
+
+  it('shows Inspected for a latest inspection that gave no grade (Rabbsfarm)', () => {
+    // Audit C1: this used to read "Good · 2025", from a 2020 ungraded visit.
+    const badge = buildOfstedListBadge({ ofsted_grade: null, ofsted_grade_date: null, ofsted_date: '2025-06-17' });
+    expect(badge.label).toBe('Inspected · 2025');
+    expect(badge.cssClass).toBe('ofstedInspected');
+  });
+
   it('returns a Report Card badge when ofsted_rc_date is present', () => {
     const badge = buildOfstedListBadge({ ofsted_grade: null, ofsted_rc_date: '2026-02-03' });
     expect(badge.label).toBe('Report Card · 2026');

nextjs-app/__tests__/support/schoolFixtures.ts

@@ -191,7 +191,8 @@ export const primaryFixture = {
     personal_development: 2,
     leadership_management: 2,
     previous_overall: 3,
-    grade_source: 'graded',
+    current_grade: { grade: 2, date: '2023-05-17', basis: 'graded' },
+    latest_visit: { date: '2023-05-17', kind: 'graded', outcome: null },
   }),
   census,
   admissions: makeAdmissions({ year: 2024 }),
@@ -295,7 +296,8 @@ export const allThroughFixture = {
     behaviour_attitudes: 1,
     personal_development: 1,
     leadership_management: 1,
-    grade_source: 'graded',
+    current_grade: { grade: 1, date: '2022-10-04', basis: 'graded' },
+    latest_visit: { date: '2022-10-04', kind: 'graded', outcome: null },
   }),
   census,
   admissions: makeAdmissions({ year: 2024, school_phase: 'Secondary' }),

nextjs-app/components/HomeView.tsx

@@ -358,10 +358,14 @@ export function HomeView({ initialSchools, filters, totalSchools, howItWorks, ed
     return () => controller.abort();
   }, [resultsView, searchParams, initialSchools.schools]);
 
-  // Fetch LA averages when secondary or mixed schools are visible
+  // Fetch LA averages when secondary or mixed schools are visible. Default
+  // cache mode, never force-cache: force-cache replays any stored response
+  // without asking the server, so one failed request (a deploy restart) hid
+  // every "vs LA avg" delta in that browser for good. The API's Cache-Control
+  // already lets the browser reuse a good answer for five minutes.
   useEffect(() => {
     if (!isSecondaryView && !isMixedView) return;
-    fetchLAaverages({ cache: 'force-cache' })
+    fetchLAaverages()
       .then(data => setLaAverages(data.secondary.attainment_8_by_la))
       .catch(() => {});
   }, [isSecondaryView, isMixedView]);

nextjs-app/components/compare/CompareAtAGlance.tsx

@@ -78,21 +78,18 @@ export function CompareAtAGlance({
           return (
             <Cell key={school.urn} school={school} index={i}>
               {display.kind === 'report_card' && <ReportCardChips summary={display.summary} />}
-              {(display.kind === 'graded' || display.kind === 'carried_forward') && (
+              {(display.kind === 'graded' || display.kind === 'confirmed') && (
                 <>
                   <span className={`${s.badge} ${display.grade <= 2 ? s.badgeGood : display.grade === 3 ? s.badgeWarn : s.badgeBad}`}>
                     {display.gradeLabel}
                   </span>
-                  {display.carriedForward && <span className={s.small}>Grade carried forward</span>}
+                  {display.kind === 'confirmed' && <span className={s.small}>Confirmed at an ungraded inspection</span>}
                 </>
               )}
-              {display.kind === 'transitional' && (
-                <>
-                  <span className={s.badge} style={{ backgroundColor: 'var(--bg-secondary)', color: 'var(--text-secondary)' }}>
-                    No overall grade
-                  </span>
-                  <span className={s.small}>Sub-judgements only</span>
-                </>
+              {display.kind === 'no_overall_grade' && (
+                <span className={s.badge} style={{ backgroundColor: 'var(--bg-secondary)', color: 'var(--text-secondary)' }}>
+                  No overall grade
+                </span>
               )}
               {display.kind === 'none' && <span className={s.small}>No inspection in our dataset</span>}
             </Cell>

nextjs-app/components/compare/CompareOfsted.tsx

@@ -1,7 +1,8 @@
 /**
  * Ofsted section — one visual grammar for inspection detail across all
- * three regimes (legacy graded, interim carried-forward, renewed-framework
- * report card). Copy comes verbatim from the reviewed mockups.
+ * three regimes (legacy graded, no overall grade, renewed-framework report
+ * card). The grade shown is the one still in force, with the inspection that
+ * awarded or confirmed it; "Inspected" is the latest visit.
  */
 
 'use client';
@@ -12,7 +13,8 @@ import {
   rcAreaLabel,
   type OfstedDisplay,
 } from '@/lib/compareLogic';
-import type { ComparisonData, OfstedInspection, School } from '@/lib/types';
+import { gradeSourceLine } from '@/lib/ofstedStatus';
+import type { ComparisonData, OfstedCurrentGrade, OfstedInspection, School } from '@/lib/types';
 import { Cell, Chip, Measure, Section, SectionGrid, sectionStyles as s } from './sectionShared';
 
 const GRADE_TONE: Record<number, 'good' | 'warn' | 'bad'> = {
@@ -39,7 +41,7 @@ function yearsSince(iso: string | null): number | null {
   return (Date.now() - d.getTime()) / (365.25 * 24 * 3600 * 1000);
 }
 
-function ResultCell({ display }: { display: OfstedDisplay }) {
+function ResultCell({ display, current }: { display: OfstedDisplay; current: OfstedCurrentGrade | null }) {
   if (display.kind === 'none') {
     return <span className={s.small}>No inspection outcome in our dataset</span>;
   }
@@ -51,15 +53,13 @@ function ResultCell({ display }: { display: OfstedDisplay }) {
       </>
     );
   }
-  if (display.kind === 'transitional') {
+  if (display.kind === 'no_overall_grade') {
     return (
       <>
         <span className={s.badge} style={{ backgroundColor: 'var(--bg-secondary)', color: 'var(--text-secondary)' }}>
           No overall grade
         </span>
-        <span className={s.small}>
-          Inspected under transitional framework (sub-judgements only)
-        </span>
+        <span className={s.small}>Ofsted stopped giving overall grades in September 2024</span>
       </>
     );
   }
@@ -68,11 +68,7 @@ function ResultCell({ display }: { display: OfstedDisplay }) {
       <span className={`${s.badge} ${display.grade <= 2 ? s.badgeGood : display.grade === 3 ? s.badgeWarn : s.badgeBad}`}>
         {display.gradeLabel}
       </span>
-      <span className={s.small}>
-        {display.carriedForward
-          ? 'Grade carried forward from an earlier inspection (ungraded visit since)'
-          : 'Overall grade (older-style inspection)'}
-      </span>
+      {current && <span className={s.small}>{gradeSourceLine(current)}</span>}
     </>
   );
 }
@@ -179,7 +175,7 @@ export function CompareOfsted({
         <Measure label="Result">
         {schools.map((school, i) => (
           <Cell key={school.urn} school={school} index={i}>
-            <ResultCell display={displays[i]} />
+            <ResultCell display={displays[i]} current={data[String(school.urn)]?.ofsted?.current_grade ?? null} />
           </Cell>
         ))}
         </Measure>
@@ -187,19 +183,15 @@ export function CompareOfsted({
         <Measure label="Inspected">
         {schools.map((school, i) => {
           const ofsted = data[String(school.urn)]?.ofsted;
-          // A report card is dated by its OWN inspection date. The legacy
-          // inspection_date belongs to an older inspection and must never
-          // be shown against a report card (report cards exist only from
-          // Nov 2025).
-          const dateIso =
-            displays[i].kind === 'report_card'
-              ? ofsted?.rc_inspection_date ?? null
-              : ofsted?.inspection_date ?? null;
+          // The school's latest visit of any kind (a report card's own date
+          // when there is one), never an older inspection a grade comes from.
+          const dateIso = ofsted?.latest_visit?.date ?? ofsted?.rc_inspection_date ?? null;
           const age = yearsSince(dateIso);
           return (
             <Cell key={school.urn} school={school} index={i}>
               {formatInspectionDate(dateIso)}{' '}
               {age != null && age > 4 && <Chip tone="neutral">4+ years ago</Chip>}
+              {ofsted?.latest_visit?.outcome && <span className={s.small}>{ofsted.latest_visit.outcome}</span>}
             </Cell>
           );
         })}

nextjs-app/components/school/NearbySchools.module.css

@@ -1,8 +1,7 @@
 .heading { font-family: var(--font-display); font-size: 1.4rem; letter-spacing: -0.4px; margin: 0; }
-.lede { margin: 0.5rem 0 1.25rem; color: var(--text-secondary); max-width: 64ch; }
 .caption { margin: 1rem 0 0; font-size: 0.72rem; color: var(--text-muted); }
 
-.top { display: flex; align-items: flex-start; justify-content: space-between; gap: 1rem; }
+.top { display: flex; align-items: center; justify-content: space-between; gap: 1rem; margin-bottom: 1.25rem; }
 .arrows { display: flex; gap: 0.5rem; flex: none; }
 .arrow { width: 44px; height: 44px; display: grid; place-items: center; cursor: pointer; border: 1px solid var(--border-strong); border-radius: 999px; background: var(--bg-card); color: var(--brand); }
 .arrow:hover:not(:disabled) { border-color: var(--brand); background: var(--brand-bg); }
@@ -15,10 +14,10 @@
 .scroller { display: grid; grid-auto-flow: column; grid-auto-columns: calc((100% - 1.8rem) / 3); gap: 0.9rem; overflow-x: auto; scroll-snap-type: x mandatory; padding: 2px; margin: -2px; list-style: none; scrollbar-width: none; -ms-overflow-style: none; }
 .scroller::-webkit-scrollbar { display: none; }
 @media (max-width: 820px) { .scroller { grid-auto-columns: calc((100% - 0.9rem) / 2); } }
-/* Touch widths (MOBILE.md): the arrows would take 96px from a 328px card and
-   crush the lede into four lines, for a control swiping already provides. They
-   go, and the documented right-edge fade carries the affordance — lifting at
-   the end of the travel, where there is nothing more to hint at. */
+/* Touch widths (MOBILE.md): the arrows would take 96px from a 328px card, for
+   a control swiping already provides. They go, and the documented right-edge
+   fade carries the affordance — lifting at the end of the travel, where there
+   is nothing more to hint at. */
 @media (max-width: 640px) {
   .top { display: block; }
   .arrows { display: none; }

nextjs-app/components/school/NearbySchoolsCarousel.tsx

@@ -4,7 +4,7 @@
  * The scroller and its arrows.
  *
  * `children` are the server-rendered cards and `header` the server-rendered
- * heading and lede: both stay server components, passed through, so this file
+ * heading: both stay server components, passed through, so this file
  * owns a DOM ref and nothing else. That is what keeps all six links in the
  * initial HTML — a carousel that mounted cards on click would put four of the
  * six beyond a crawler and beyond a reader with no JavaScript.

nextjs-app/components/school/NearbySchoolsSection.tsx

@@ -13,8 +13,10 @@
  * reached on their behalf.
  *
  * There is deliberately no "how these are chosen" panel: the method is already
- * visible in the lede, the chips and the distances. The single caption line is
- * not a method note — it is the one thing a card cannot self-correct.
+ * visible in the chips and the distances. The single caption line is not a
+ * method note — it is the one thing a card cannot self-correct.
+ *
+ * Nor is there a lede: "Other primary schools near X" only restated the heading.
  */
 
 import Link from 'next/link';
@@ -32,28 +34,6 @@ export function shouldRenderNearby(nearby?: NearbySchool[] | null): boolean {
   return (nearby?.length ?? 0) >= MINIMUM;
 }
 
-/**
- * What the lede calls the set of schools it is showing.
- *
- * Derived from the school's own GIAS phase rather than the template it renders
- * with, because those disagree for "16 plus" (GIAS phase 6): a sixth-form
- * college renders the primary template — computeSchoolFlags tests for the
- * substring "secondary" — while the backend correctly matches it against the
- * secondary group. Taking the noun from the template would print "Other primary
- * schools near <sixth form college>" above a row of secondaries.
- *
- * A 16-plus school's candidates span the whole secondary group, so no single
- * noun fits and it gets the honest general one.
- */
-export function nearbyNoun(phase: string | null | undefined): string {
-  const text = (phase ?? '').trim().toLowerCase();
-  if (text === 'all-through') return 'all-through schools';
-  if (text === '16 plus') return 'schools and colleges';
-  if (text.includes('secondary')) return 'secondary schools';
-  if (text.includes('primary')) return 'primary schools';
-  return 'schools';
-}
-
 function metricLabel(key: string): string {
   return key === 'attainment_8_score' ? 'Attainment 8' : 'Reading, writing & maths';
 }
@@ -65,25 +45,16 @@ function formatMetric(value: number | null, key: string): string {
 
 export function NearbySchoolsSection({
   urn,
-  schoolName,
-  phase,
   thisMetricValue,
   nearby,
 }: {
   urn: number;
-  schoolName: string;
-  /** The school's own GIAS phase, not the template it renders with. */
-  phase: string | null | undefined;
   thisMetricValue: number | null;
   nearby?: NearbySchool[] | null;
 }) {
   if (!shouldRenderNearby(nearby)) return null;
   const schools = nearby as NearbySchool[];
-
-  // One card matched on phase alone, so the section may not claim the set
-  // shares an intake with this school.
   const metricKey = schools[0].metric_key;
-  const noun = nearbyNoun(phase);
 
   return (
     <Section id="nearby">
@@ -91,12 +62,9 @@ export function NearbySchoolsSection({
         count={schools.length}
         labelledBy="nearby-schools-heading"
         header={
-          <div>
-            <h2 id="nearby-schools-heading" className={styles.heading}>
-              Other schools nearby
-            </h2>
-            <p className={styles.lede}>{`Other ${noun} near ${schoolName}.`}</p>
-          </div>
+          <h2 id="nearby-schools-heading" className={styles.heading}>
+            Other schools nearby
+          </h2>
         }
       >
         {schools.map((school) => (

nextjs-app/components/school/OfstedSection.tsx

@@ -1,16 +1,18 @@
 /**
  * OfstedSection — shared between the primary and secondary detail pages.
  *
- * The two versions were ~80% identical, but that figure masked a real fork in
- * the no-overall-grade case: the primary page shows a "Not rated" badge, while
- * the secondary page shows a four-area OEIF panel. The disclaimer copy also
- * differs slightly. Both are preserved exactly via the `variant` prop rather
- * than reconciled, because this refactor must not change either page. Merging
- * them is a follow-up decision for a human, not a side effect of a move.
+ * The headline is the school's current Ofsted status (backend:
+ * fact_ofsted_latest): the report card; or the overall grade still in force,
+ * with the inspection that awarded or confirmed it; or "No overall grade".
+ * A later visit that is not the grade's source gets its own line. Both pages
+ * render the same branches, so neither drops an area judgement (audit M2).
+ * Rule: docs/superpowers/specs/2026-10-05-ofsted-current-status-design.md
  *
  * Server component.
  */
 
+import { ofstedDisplay } from '@/lib/compareLogic';
+import { formatOfstedDate, gradeSourceLine, latestVisitLine, showLatestVisitLine } from '@/lib/ofstedStatus';
 import type { OfstedInspection } from '@/lib/types';
 import { Section, sectionStyles as styles } from './sectionShared';
 
@@ -40,14 +42,13 @@ export interface OfstedSectionProps {
   ofstedInspectedDate: string | null;
   oeifAllSameGrade: boolean;
   oeifAreas: { label: string; value: number }[];
-  variant?: 'primary' | 'secondary';
 }
 
 export function OfstedSection({
   ofsted, urn, isReportCard, ofstedInspectedDate,
-  oeifAllSameGrade, oeifAreas, variant = 'primary',
+  oeifAllSameGrade, oeifAreas,
 }: OfstedSectionProps) {
-  const isSecondary = variant === 'secondary';
+  const display = ofstedDisplay(ofsted);
 
   return (
     <Section id="ofsted">
@@ -55,7 +56,7 @@ export function OfstedSection({
         {isReportCard ? 'Ofsted Report Card' : 'Ofsted Rating'}
         {ofstedInspectedDate && (
           <span className={styles.ofstedDate}>
-            {isSecondary && ' '}Inspected {new Date(ofstedInspectedDate).toLocaleDateString('en-GB', { day: 'numeric', month: 'long', year: 'numeric' })}
+            Inspected {new Date(ofstedInspectedDate).toLocaleDateString('en-GB', { day: 'numeric', month: 'long', year: 'numeric' })}
           </span>
         )}
         <a
@@ -98,65 +99,55 @@ export function OfstedSection({
             })}
           </div>
         </>
-      ) : (!isSecondary || ofsted.overall_effectiveness) ? (
-        /* ── Old OEIF layout ── */
+      ) : (
         <>
           <div className={styles.ofstedHeader}>
-            <span className={`${styles.ofstedGrade} ${styles[`ofstedGrade${ofsted.overall_effectiveness}`]}`}>
-              {ofsted.overall_effectiveness ? OFSTED_LABELS[ofsted.overall_effectiveness] : 'Not rated'}
-            </span>
-            {ofsted.previous_overall != null &&
-              ofsted.previous_overall !== ofsted.overall_effectiveness && (
-              <span className={styles.ofstedPrevious}>
-                Previously: {OFSTED_LABELS[ofsted.previous_overall]}
-              </span>
+            {display.kind === 'graded' || display.kind === 'confirmed' ? (
+              <>
+                <span className={`${styles.ofstedGrade} ${styles[`ofstedGrade${display.grade}`]}`}>
+                  {display.gradeLabel}
+                </span>
+                {ofsted.previous_overall != null && ofsted.previous_overall !== display.grade && (
+                  <span className={styles.ofstedPrevious}>
+                    Previously: {OFSTED_LABELS[ofsted.previous_overall]}
+                  </span>
+                )}
+              </>
+            ) : (
+              <span className={styles.ofstedGrade}>No overall grade</span>
             )}
           </div>
           <p className={styles.ofstedDisclaimer}>
-            {ofsted.grade_source === 'ungraded_carried_forward'
-              ? 'This overall grade is carried forward from an earlier inspection. Ofsted has since visited without issuing a new overall grade. From September 2024, Ofsted no longer makes an overall effectiveness judgement.'
-              : isSecondary
-                ? 'From September 2024, Ofsted no longer makes an overall effectiveness judgement in inspections.'
-                : 'From September 2024, Ofsted no longer makes an overall effectiveness judgement in inspections of state-funded schools.'}
+            {ofsted.current_grade
+              ? gradeSourceLine(ofsted.current_grade)
+              : 'Ofsted stopped giving overall grades in September 2024.'}
           </p>
-          {oeifAllSameGrade ? (
-            <p className={styles.ofstedAllSame}>
-              Rated <strong>{OFSTED_LABELS[ofsted.overall_effectiveness!]}</strong> across all inspected areas: Quality of Teaching, Behaviour, Pupils&apos; Development and Leadership.
-            </p>
-          ) : (
-            <div className={`${styles.metricsGrid} ${styles.gradeGrid}`}>
-              {oeifAreas.map(({ label, value }) => (
-                <div key={label} className={styles.metricCard}>
-                  <div className={styles.metricLabel}>{label}</div>
-                  <div className={`${styles.metricValue} ${styles[`ofstedGrade${value}`]}`}>
-                    {OFSTED_LABELS[value]}
-                  </div>
-                </div>
-              ))}
-            </div>
+          {showLatestVisitLine(ofsted) && ofsted.latest_visit && (
+            <p className={styles.ofstedDisclaimer}>Latest visit: {latestVisitLine(ofsted.latest_visit)}</p>
           )}
-        </>
-      ) : (
-        /* ── Secondary only: inspected since Sept 2024, no overall grade ── */
-        <>
-          <p className={styles.sectionSubtitle}>
-            From September 2024, Ofsted no longer gives a single overall grade.
-          </p>
-          <div className={`${styles.metricsGrid} ${styles.gradeGrid}`}>
-            {[
-              { label: 'Quality of Education', value: ofsted.quality_of_education },
-              { label: 'Behaviour & Attitudes', value: ofsted.behaviour_attitudes },
-              { label: 'Personal Development', value: ofsted.personal_development },
-              { label: 'Leadership & Management', value: ofsted.leadership_management },
-            ].filter(({ value }) => value != null).map(({ label, value }) => (
-              <div key={label} className={styles.metricCard}>
-                <div className={styles.metricLabel}>{label}</div>
-                <div className={`${styles.metricValue} ${styles[`ofstedGrade${value}`]}`}>
-                  {OFSTED_LABELS[value!]}
-                </div>
+          {oeifAllSameGrade && (display.kind === 'graded' || display.kind === 'confirmed') ? (
+            <p className={styles.ofstedAllSame}>
+              Rated <strong>{display.gradeLabel}</strong> across all inspected areas: Quality of Teaching, Behaviour, Pupils&apos; Development and Leadership.
+            </p>
+          ) : oeifAreas.length > 0 ? (
+            <>
+              {ofsted.inspection_date && ofsted.inspection_date !== ofsted.latest_visit?.date && (
+                <p className={styles.ofstedDisclaimer}>
+                  Area judgements from the graded inspection, {formatOfstedDate(ofsted.inspection_date)}.
+                </p>
+              )}
+              <div className={`${styles.metricsGrid} ${styles.gradeGrid}`}>
+                {oeifAreas.map(({ label, value }) => (
+                  <div key={label} className={styles.metricCard}>
+                    <div className={styles.metricLabel}>{label}</div>
+                    <div className={`${styles.metricValue} ${styles[`ofstedGrade${value}`]}`}>
+                      {OFSTED_LABELS[value]}
+                    </div>
+                  </div>
+                ))}
               </div>
-            ))}
-          </div>
+            </>
+          ) : null}
         </>
       )}
     </Section>

nextjs-app/components/school/PrimarySchoolSections.tsx

@@ -55,15 +55,17 @@ export function PrimarySchoolSections({
   const secondaryAvg = nationalAvg?.secondary ?? {};
 
   const isReportCard = !!(ofsted?.report_card && Object.keys(ofsted.report_card).length > 0);
-  // Report cards are dated by their own inspection (rc_inspection_date), never
-  // the legacy inspection_date (report cards exist only from Nov 2025).
+  // Report cards are dated by their own inspection (rc_inspection_date);
+  // anything else by the school's latest visit, never the older inspection a
+  // grade may come from.
   const ofstedInspectedDate = isReportCard
     ? ofsted?.rc_inspection_date ?? null
-    : ofsted?.inspection_date ?? null;
+    : ofsted?.latest_visit?.date ?? null;
   const oeifAreas = ofsted ? ofstedLegacyAreas(ofsted) : [];
   const oeifAllSameGrade =
     !!ofsted &&
     !isReportCard &&
+    ofsted.overall_effectiveness != null &&
     oeifAreas.length >= 3 &&
     oeifAreas.every((a) => a.value === ofsted.overall_effectiveness);
 
@@ -77,7 +79,6 @@ export function PrimarySchoolSections({
           ofstedInspectedDate={ofstedInspectedDate}
           oeifAllSameGrade={oeifAllSameGrade}
           oeifAreas={oeifAreas}
-          variant="primary"
         />
       )}
 
@@ -154,8 +155,6 @@ export function PrimarySchoolSections({
       {/* Last: it is where the reader goes next, not part of this school. */}
       <NearbySchoolsSection
         urn={schoolInfo.urn}
-        schoolName={schoolInfo.school_name}
-        phase={schoolInfo.phase}
         thisMetricValue={flags.latestResults?.rwm_expected_pct ?? null}
         nearby={nearbySchools}
       />

nextjs-app/components/school/SecondarySchoolSections.tsx

@@ -63,11 +63,12 @@ export function SecondarySchoolSections({
   const isReportCard = !!(ofsted?.report_card && Object.keys(ofsted.report_card).length > 0);
   const ofstedInspectedDate = isReportCard
     ? ofsted?.rc_inspection_date ?? null
-    : ofsted?.inspection_date ?? null;
+    : ofsted?.latest_visit?.date ?? null;
   const oeifAreas = ofsted ? ofstedLegacyAreas(ofsted) : [];
   const oeifAllSameGrade =
     !!ofsted &&
     !isReportCard &&
+    ofsted.overall_effectiveness != null &&
     oeifAreas.length >= 3 &&
     oeifAreas.every((a) => a.value === ofsted.overall_effectiveness);
 
@@ -81,7 +82,6 @@ export function SecondarySchoolSections({
           ofstedInspectedDate={ofstedInspectedDate}
           oeifAllSameGrade={oeifAllSameGrade}
           oeifAreas={oeifAreas}
-          variant="secondary"
         />
       )}
 
@@ -148,8 +148,6 @@ export function SecondarySchoolSections({
       {/* Last: it is where the reader goes next, not part of this school. */}
       <NearbySchoolsSection
         urn={schoolInfo.urn}
-        schoolName={schoolInfo.school_name}
-        phase={schoolInfo.phase}
         thisMetricValue={flags.latestResults?.attainment_8_score ?? null}
         nearby={nearbySchools}
       />

nextjs-app/lib/compareLogic.ts

@@ -100,9 +100,8 @@ export function summariseReportCard(ofsted: OfstedInspection): ReportCardSummary
 
 export type OfstedDisplay =
   | { kind: 'none' }
-  | { kind: 'graded'; grade: number; gradeLabel: string; carriedForward: false }
-  | { kind: 'carried_forward'; grade: number; gradeLabel: string; carriedForward: true }
-  | { kind: 'transitional' }
+  | { kind: 'graded' | 'confirmed'; grade: number; gradeLabel: string; gradeDate: string | null }
+  | { kind: 'no_overall_grade' }
   | { kind: 'report_card'; summary: ReportCardSummary };
 
 export function ofstedDisplay(
@@ -116,19 +115,19 @@ export function ofstedDisplay(
     return { kind: 'report_card', summary: summariseReportCard(ofsted) };
   }
 
-  const grade = ofsted.overall_effectiveness;
-  const gradeLabel = grade != null ? OFSTED_LEGACY_GRADES[grade] : undefined;
-  if (grade == null || gradeLabel === undefined) {
-    if (ofsted.inspection_date) {
-      return { kind: 'transitional' };
-    }
-    return { kind: 'none' };
+  // The grade still in force (backend: fact_ofsted_latest), never one carried
+  // past a later inspection that gave none.
+  const current = ofsted.current_grade;
+  const gradeLabel = current ? OFSTED_LEGACY_GRADES[current.grade] : undefined;
+  if (current && gradeLabel !== undefined) {
+    return {
+      kind: current.basis === 'confirmed' ? 'confirmed' : 'graded',
+      grade: current.grade,
+      gradeLabel,
+      gradeDate: current.date,
+    };
   }
-
-  if (ofsted.grade_source === 'ungraded_carried_forward') {
-    return { kind: 'carried_forward', grade, gradeLabel, carriedForward: true };
-  }
-  return { kind: 'graded', grade, gradeLabel, carriedForward: false };
+  return ofsted.latest_visit ? { kind: 'no_overall_grade' } : { kind: 'none' };
 }
 
 // ---------------------------------------------------------------------------

nextjs-app/lib/ofstedStatus.ts

@@ -0,0 +1,48 @@
+/**
+ * The sentences the school page and the compare page print about where an
+ * Ofsted grade came from and what the latest visit was. One wording, two pages.
+ * Rule: docs/superpowers/specs/2026-10-05-ofsted-current-status-design.md
+ */
+
+import type { OfstedCurrentGrade, OfstedInspection, OfstedLatestVisit } from './types';
+
+export function formatOfstedDate(iso: string | null | undefined): string {
+  if (!iso) return '';
+  const d = new Date(iso);
+  if (Number.isNaN(d.getTime())) return '';
+  return d.toLocaleDateString('en-GB', { day: 'numeric', month: 'long', year: 'numeric' });
+}
+
+const VISIT_KIND: Record<OfstedLatestVisit['kind'], string> = {
+  report_card: 'Report card inspection',
+  graded: 'Graded inspection',
+  ungraded: 'Ungraded inspection',
+};
+
+/** "Graded inspection, 6 July 2016" or "Confirmed at an ungraded inspection, 14 March 2023". */
+export function gradeSourceLine(current: OfstedCurrentGrade): string {
+  const when = formatOfstedDate(current.date);
+  const what = current.basis === 'confirmed' ? 'Confirmed at an ungraded inspection' : 'Graded inspection';
+  return when ? `${what}, ${when}` : what;
+}
+
+/** "Ungraded inspection, 13 November 2024: Standards maintained". */
+export function latestVisitLine(visit: OfstedLatestVisit): string {
+  const head = `${VISIT_KIND[visit.kind]}, ${formatOfstedDate(visit.date)}`;
+  return visit.outcome ? `${head}: ${visit.outcome}` : head;
+}
+
+/**
+ * Whether the latest visit needs its own line: when it is not where the grade
+ * came from, or when there is no grade but an ungraded outcome to report. A
+ * graded visit without a grade is already dated by the section title.
+ */
+export function showLatestVisitLine(
+  ofsted: Pick<OfstedInspection, 'current_grade' | 'latest_visit'>,
+): boolean {
+  const visit = ofsted.latest_visit;
+  if (!visit || visit.kind === 'report_card') return false;
+  const current = ofsted.current_grade;
+  if (current) return current.date !== visit.date;
+  return visit.kind === 'ungraded';
+}

nextjs-app/lib/types.ts

@@ -76,10 +76,14 @@ export interface School {
   parliamentary_constituency?: string | null;
 
   // Ofsted (for list view — summary only)
+  /** The overall grade still in force; null when the latest inspection gave none. */
   ofsted_grade?: 1 | 2 | 3 | 4 | null;
+  /** Date the grade was awarded or confirmed (null without a grade). */
+  ofsted_grade_date?: string | null;
   /** Report-card inspection date (Nov 2025+); non-null identifies a report
    * card in the list/map, where the full report_card object isn't available. */
   ofsted_rc_date?: string | null;
+  /** The school's latest inspection of any kind. */
   ofsted_date?: string | null;
   ofsted_framework?: string | null;
 }
@@ -95,6 +99,7 @@ export interface OfstedInspection {
   rc_inspection_date?: string | null;
   inspection_type: string | null;
   // OEIF fields (old framework, pre-Nov 2025)
+  /** The graded inspection's own overall grade; never carried forward. */
   overall_effectiveness: 1 | 2 | 3 | 4 | null;
   quality_of_education: number | null;
   behaviour_attitudes: number | null;
@@ -115,9 +120,12 @@ export interface OfstedInspection {
   rc_leadership_governance: number | null;
   rc_early_years: number | null;
   rc_sixth_form: number | null;
-  /** Where the effective overall grade came from: a graded (Section 5)
-   * inspection, or carried forward from an ungraded (Section 8) outcome. */
-  grade_source?: 'graded' | 'ungraded_carried_forward' | null;
+  /** The overall grade still in force, dated by the inspection that awarded
+   * ("graded") or confirmed ("confirmed", an ungraded visit) it. Null when the
+   * latest inspection gave no overall grade, or for a report card. */
+  current_grade?: OfstedCurrentGrade | null;
+  /** The school's most recent inspection of any kind. */
+  latest_visit?: OfstedLatestVisit | null;
   /** Renewed-framework (Nov 2025) area judgements, coded + labelled by the
    * backend from the live-sampled Ofsted vocabulary. Empty when the school
    * has no report-card inspection. Safeguarding is never included here. */
@@ -127,6 +135,18 @@ export interface OfstedInspection {
   report_url?: string | null;
 }
 
+export interface OfstedCurrentGrade {
+  grade: 1 | 2 | 3 | 4;
+  date: string | null;
+  basis: 'graded' | 'confirmed';
+}
+
+export interface OfstedLatestVisit {
+  date: string;
+  kind: 'report_card' | 'graded' | 'ungraded';
+  outcome: string | null;
+}
+
 export interface ReportCardEntry {
   code: number;
   label: string;

nextjs-app/lib/utils.ts

@@ -2,7 +2,7 @@
  * Utility functions for SchoolCompare
  */
 
-import type { School, MetricDefinition, OfstedInspection, SchoolAdmissions, SchoolResult } from './types';
+import type { School, MetricDefinition } from './types';
 
 // ============================================================================
 // String Utilities
@@ -619,172 +619,6 @@ export function getCurrentAcademicYear(): number {
   return month >= 8 ? year : year - 1;
 }
 
-// ============================================================================
-// School Detail Hero Helpers
-// ============================================================================
-
-const OFSTED_OEIF_WORDS: Record<number, string> = {
-  1: 'Outstanding', 2: 'Good', 3: 'Requires Improvement', 4: 'Inadequate',
-};
-
-/**
- * Format an Ofsted inspection date as "Month YYYY" (e.g. "November 2023").
- */
-function formatOfstedMonth(date: string | null | undefined): string {
-  if (!date) return '';
-  const d = new Date(date);
-  if (Number.isNaN(d.getTime())) return '';
-  return d.toLocaleDateString('en-GB', { month: 'long', year: 'numeric' });
-}
-
-export type HeroTone = 'teal' | 'green' | 'gold' | 'coral' | 'neutral';
-
-export interface OfstedHeroChip {
-  state: 'oeif' | 'reportCard' | 'none';
-  title: string;           // Main label (e.g. "Ofsted Outstanding", "Ofsted Report Card")
-  subtitle: string;        // Context line (e.g. "Inspected November 2023")
-  detail?: string;         // Optional extra line (e.g. "Safeguarding: Met")
-  tone: HeroTone;          // Maps to dedicated hero tone classes (not badge classes)
-}
-
-/**
- * Build the hero-strip Ofsted chip, branching on the inspection framework.
- * Never synthesises a single overall grade for ReportCard schools.
- *
- * Note: the API may return ``framework`` as a literal string ``"NULL"`` for
- * older inspections, so we explicitly only branch into the ReportCard layout
- * when the value is exactly ``"ReportCard"``. Anything else with an
- * ``overall_effectiveness`` score is treated as OEIF.
- */
-export function buildOfstedHeroChip(ofsted: OfstedInspection | null | undefined): OfstedHeroChip {
-  if (!ofsted) {
-    return {
-      state: 'none',
-      title: 'Ofsted pending',
-      subtitle: 'No inspection on record',
-      tone: 'neutral',
-    };
-  }
-
-  const when = formatOfstedMonth(ofsted.inspection_date);
-
-  // ReportCard branch — only if the API explicitly says so
-  if (ofsted.framework === 'ReportCard') {
-    const safeguarding = ofsted.rc_safeguarding_met;
-    return {
-      state: 'reportCard',
-      title: 'Ofsted Report Card',
-      subtitle: when ? `Inspected ${when}` : 'New framework inspection',
-      detail:
-        safeguarding == null
-          ? undefined
-          : safeguarding ? 'Safeguarding: Met' : 'Safeguarding: Not met',
-      tone: safeguarding === false ? 'coral' : 'green',
-    };
-  }
-
-  // Otherwise treat as OEIF (covers framework === 'OEIF', null, "NULL", etc.)
-  const grade = ofsted.overall_effectiveness;
-  if (grade && OFSTED_OEIF_WORDS[grade]) {
-    const oeifTone: HeroTone =
-      grade === 1 ? 'teal' :
-      grade === 2 ? 'green' :
-      grade === 3 ? 'gold' :
-      'coral';
-    return {
-      state: 'oeif',
-      title: `Ofsted ${OFSTED_OEIF_WORDS[grade]}`,
-      subtitle: when ? `Inspected ${when}` : 'Inspected',
-      tone: oeifTone,
-    };
-  }
-
-  return {
-    state: 'oeif',
-    title: 'Ofsted inspected',
-    subtitle: when ? `Inspected ${when}` : 'Inspection on record',
-    tone: 'neutral',
-  };
-}
-
-/**
- * Build a one-sentence editorial summary for the school detail hero.
- * Branches on Ofsted framework so Report Card schools are never described
- * with an overall grade they do not have.
- */
-export function buildSchoolSummary(
-  schoolInfo: School,
-  ofsted: OfstedInspection | null | undefined,
-  admissions: SchoolAdmissions | null | undefined,
-  latestResults: SchoolResult | null | undefined,
-): string {
-  const parts: string[] = [];
-
-  // Size descriptor
-  const pupils = latestResults?.total_pupils ?? schoolInfo.total_pupils ?? null;
-  const sizeWord =
-    pupils == null ? '' :
-    pupils < 200 ? 'Small' :
-    pupils < 500 ? 'Mid-sized' :
-    'Large';
-
-  // Phase descriptor — avoid the raw code
-  const phase = (schoolInfo.phase ?? '').toLowerCase();
-  const phaseWord =
-    phase.includes('secondary') ? 'secondary' :
-    phase === 'all-through' ? 'all-through' :
-    phase.includes('primary') ? 'primary' :
-    'school';
-
-  // Religious character
-  const religion = schoolInfo.religious_denomination;
-  const religionWord =
-    !religion || /none|does not apply/i.test(religion) ? '' :
-    /roman catholic|catholic/i.test(religion) ? 'Catholic ' :
-    /church of england|ce|anglican/i.test(religion) ? 'Church of England ' :
-    /jewish/i.test(religion) ? 'Jewish ' :
-    /muslim|islam/i.test(religion) ? 'Muslim ' :
-    /hindu/i.test(religion) ? 'Hindu ' :
-    /sikh/i.test(religion) ? 'Sikh ' :
-    '';
-
-  // Locality — prefer town from address parsing (fallback to LA)
-  const locality = schoolInfo.town || schoolInfo.local_authority || '';
-
-  const lead = [sizeWord, religionWord + phaseWord].filter(Boolean).join(' ');
-  let opening = lead || 'School';
-  if (locality) opening += ` in ${locality}`;
-  parts.push(opening);
-
-  // Ofsted clause (framework-aware)
-  if (ofsted?.framework === 'OEIF' && ofsted.overall_effectiveness) {
-    parts.push(`rated ${OFSTED_OEIF_WORDS[ofsted.overall_effectiveness]} by Ofsted`);
-  } else if (ofsted?.framework === 'ReportCard') {
-    const when = formatOfstedMonth(ofsted.inspection_date);
-    parts.push(
-      when
-        ? `most recently inspected under Ofsted's Report Card framework in ${when}`
-        : "recently inspected under Ofsted's new Report Card framework",
-    );
-  }
-
-  // Admissions clause
-  if (admissions?.oversubscribed) {
-    if (admissions.first_preference_offer_pct != null) {
-      const pct = Math.round(admissions.first_preference_offer_pct);
-      parts.push(
-        `oversubscribed (${pct}% of first-choice applicants are offered a place)`,
-      );
-    } else {
-      parts.push('oversubscribed');
-    }
-  } else if (admissions?.first_preference_offer_pct != null && admissions.first_preference_offer_pct >= 90) {
-    parts.push('most families get their first-choice offer');
-  }
-
-  return parts.join(', ') + '.';
-}
-
 // ─── Legacy (OEIF) sub-judgement areas ────────────────────────────────────────
 
 export interface OfstedLegacyArea {
@@ -837,15 +671,18 @@ export interface OfstedListBadge {
  *     Checked FIRST so it wins over any carried-forward legacy grade — the
  *     list has no full report_card object, and ofsted_framework is the raw
  *     event grouping ("Schools - S5"), never "ReportCard".
- *   - OEIF school (ofsted_grade set): grade word + year, colour-keyed
- *   - Inspected without an overall grade (OEIF post-Sept-2024, where Ofsted no
- *     longer issues an overall judgement): "Inspected · YYYY" — mirrors the
- *     detail page's hero chip so a school never reads as both inspected and
+ *   - Current grade (ofsted_grade set): grade word + the year it was awarded
+ *     or confirmed (ofsted_grade_date), colour-keyed. Never the year of a later
+ *     visit: that paired old grades with new inspections (audit C1).
+ *   - Inspected with no grade in force (every inspection Sept 2024 – Nov 2025,
+ *     or an ungraded visit whose outcome names no grade): "Inspected · YYYY",
+ *     dated by the latest visit, so a school never reads as both inspected and
  *     "Not yet inspected"
  *   - No inspection on record: "Not yet inspected" in grey
  */
 export function buildOfstedListBadge(school: {
   ofsted_grade?: 1 | 2 | 3 | 4 | null;
+  ofsted_grade_date?: string | null;
   ofsted_date?: string | null;
   ofsted_framework?: string | null;
   ofsted_rc_date?: string | null;
@@ -858,10 +695,7 @@ export function buildOfstedListBadge(school: {
     return { label: `Report Card · ${rcYear}`, cssClass: 'ofstedRc' };
   }
 
-  const year = school.ofsted_date
-    ? new Date(school.ofsted_date).getFullYear()
-    : null;
-  const yearStr = year ? ` · ${year}` : '';
+  const yearOf = (iso?: string | null) => (iso ? new Date(iso).getFullYear() : null);
 
   if (school.ofsted_grade) {
     const labels: Record<number, string> = {
@@ -870,17 +704,19 @@ export function buildOfstedListBadge(school: {
       3: 'Req. Improvement',
       4: 'Inadequate',
     };
+    const gradeYear = yearOf(school.ofsted_grade_date);
     return {
-      label: `${labels[school.ofsted_grade]}${yearStr}`,
+      label: `${labels[school.ofsted_grade]}${gradeYear ? ` · ${gradeYear}` : ''}`,
       cssClass: `ofsted${school.ofsted_grade}`,
     };
   }
 
-  // An inspection is on record (date or framework present) but carries no
-  // overall grade — a post-Sept-2024 OEIF inspection. Distinct from a school
-  // that has genuinely never been inspected.
+  // An inspection is on record but no overall grade is in force: every
+  // inspection from Sept 2024 to Nov 2025, or an ungraded visit whose outcome
+  // names no grade. Dated by the latest visit.
   if (school.ofsted_date != null || school.ofsted_framework != null) {
-    return { label: `Inspected${yearStr}`, cssClass: 'ofstedInspected' };
+    const visitYear = yearOf(school.ofsted_date);
+    return { label: `Inspected${visitYear ? ` · ${visitYear}` : ''}`, cssClass: 'ofstedInspected' };
   }
 
   return { label: 'Not yet inspected', cssClass: 'ofstedPending' };

pipeline/dags/school_data_pipeline.py

@@ -106,9 +106,12 @@ print(f'Validation passed: {{count}} GIAS rows')
         """,
     )
 
+    # Marts fed by annual EES staging models are rebuilt by the EES DAG, even
+    # when they join dim_school. Selecting them here fails in any database
+    # where that DAG hasn't run (pipeline/tests/test_dag_selectors.py).
     dbt_build = BashOperator(
         task_id="dbt_build",
-        bash_command=f"cd {PIPELINE_DIR}/transform && {DBT_BIN} build --profiles-dir . --target production --select stg_gias_establishments+ stg_gias_links+ gias_code_names+ --exclude int_ks2_with_lineage+ int_ks4_with_lineage+",
+        bash_command=f"cd {PIPELINE_DIR}/transform && {DBT_BIN} build --profiles-dir . --target production --select stg_gias_establishments+ stg_gias_links+ gias_code_names+ --exclude int_ks2_with_lineage+ int_ks4_with_lineage+ stg_ees_ks4_destinations+ stg_ees_ks5_destinations+",
     )
 
     sync_typesense = BashOperator(
@@ -143,7 +146,7 @@ with DAG(
 
     dbt_build_ofsted = BashOperator(
         task_id="dbt_build",
-        bash_command=f"cd {PIPELINE_DIR}/transform && {DBT_BIN} build --profiles-dir . --target production --select stg_ofsted_inspections+ int_ofsted_latest+ fact_ofsted_inspection+ dim_school+",
+        bash_command=f"cd {PIPELINE_DIR}/transform && {DBT_BIN} build --profiles-dir . --target production --select stg_ofsted_inspections+ int_ofsted_latest+ fact_ofsted_inspection+ dim_school+ --exclude stg_ees_ks4_destinations+ stg_ees_ks5_destinations+",
     )
 
     sync_typesense_ofsted = BashOperator(
@@ -190,7 +193,7 @@ with DAG(
 
     dbt_build_ees = BashOperator(
         task_id="dbt_build",
-        bash_command=f"cd {PIPELINE_DIR}/transform && {DBT_BIN} build --profiles-dir . --target production --select stg_ees_ks2+ stg_legacy_ks2+ stg_ees_ks4+ stg_legacy_ks4+ stg_ees_census+ stg_ees_admissions+ stg_ees_ks2_national+ stg_ees_ks4_national+ stg_ees_ks4_destinations+ stg_ees_ks5_destinations+ stg_ees_ks4_destinations_national+ stg_ees_ks5_destinations_national+",
+        bash_command=f"cd {PIPELINE_DIR}/transform && {DBT_BIN} build --profiles-dir . --target production --select stg_ees_ks2+ stg_legacy_ks2+ stg_ees_ks4+ stg_legacy_ks4+ stg_ees_census+ stg_ees_admissions+ stg_ees_ks2_national+ stg_ees_ks4_national+ stg_ees_ks4_la+ stg_ees_ks4_destinations+ stg_ees_ks5_destinations+ stg_ees_ks4_destinations_national+ stg_ees_ks5_destinations_national+",
     )
 
     sync_typesense_ees = BashOperator(

pipeline/plugins/extractors/tap-uk-ees/tap_uk_ees/ks4_info.py

@@ -0,0 +1,47 @@
+"""KS4 school information: the fields the stream declares, and the older
+names DfE used for them.
+
+2023/24 information exists only in the 2023/24 release, whose
+202324_information_about_schools_final.csv (re-issued 10 March 2026) uses the
+older names. Without the renames every 2023/24 field loaded as null (audit C2).
+Newer files contain none of the older names, so the renames leave them alone.
+
+Free of the Singer SDK so CI's pytest can load it.
+"""
+
+# Declared Singer fields besides the required time_period and school_urn.
+KS4_INFO_FIELDS = (
+    "school_laestab",
+    "school_name",
+    "establishment_type_group",
+    "reldenom",
+    "admpol_pt",
+    "egender",
+    "agerange",
+    "allks_pupil_count",
+    "allks_boys_count",
+    "allks_girls_count",
+    "endks4_pupil_count",
+    "ks2_scaledscore_average",
+    "sen_with_ehcp_pupil_percent",
+    "sen_pupil_percent",
+    "sen_no_ehcp_pupil_percent",
+    "attainment8_diffn",
+    "progress8_diffn",
+    "progress8_banding",
+)
+
+# 2023/24 column name → declared field.
+KS4_INFO_RENAMES = {
+    "t_allks_pupils": "allks_pupil_count",
+    "t_allks_boys": "allks_boys_count",
+    "t_allks_girls": "allks_girls_count",
+    "t_pupils": "endks4_pupil_count",
+    "avg_ks2_scaledscore": "ks2_scaledscore_average",
+    "pt_sen_with_ehcp": "sen_with_ehcp_pupil_percent",
+    "pt_sen": "sen_pupil_percent",
+    "pt_sen_no_ehcp": "sen_no_ehcp_pupil_percent",
+    "diffn_att8": "attainment8_diffn",
+    "diffn_p8mea": "progress8_diffn",
+    "p8_banding": "progress8_banding",
+}

pipeline/plugins/extractors/tap-uk-ees/tap_uk_ees/ks4_summary.py

@@ -0,0 +1,56 @@
+"""DfE's KS4 "summary, all state-funded" data set (Key stage 4 performance).
+
+One CSV holds England, regional and local-authority headline rows for every
+year since 2018/19. The England stream (ees_ks4_national) and the LA stream
+(ees_ks4_la) both read it. Its LA rows match DfE's published performance-table
+LA averages exactly (audit H2). Suppressed values ('z', 'x') become NULL in
+dbt; Progress 8 is 'z' in years with no KS2 baseline (2024/25): DfE policy,
+not missing data.
+
+Free of the Singer SDK so CI's pytest can load it.
+"""
+from __future__ import annotations
+
+import pandas as pd
+
+KS4_SUMMARY_CSV_URL = (
+    "https://explore-education-statistics.service.gov.uk/data-catalogue/"
+    "data-set/1b649e16-01e8-435b-a814-56be2faf9054/csv"
+)
+
+# CSV column → Singer field: the same 8 headline measures at every level.
+KS4_HEADLINE_COL_MAP = {
+    "attainment8_average":    "attainment_8_score",
+    "progress8_average":      "progress_8_score",
+    "engmath_94_percent":     "english_maths_standard_pass_pct",
+    "engmath_95_percent":     "english_maths_strong_pass_pct",
+    "ebacc_entering_percent": "ebacc_entry_pct",
+    "ebacc_94_percent":       "ebacc_standard_pass_pct",
+    "ebacc_95_percent":       "ebacc_strong_pass_pct",
+    "ebacc_aps_average":      "ebacc_avg_score",
+}
+
+
+def headline_rows(df: pd.DataFrame, geographic_level: str) -> pd.DataFrame:
+    """All-pupil rows for all state-funded schools at one geographic level
+    ("National" or "Local authority"). Column names are lower-cased first;
+    a filter column the file lacks is not applied."""
+    df = df.copy()
+    df.columns = [c.strip().lower() for c in df.columns]
+    for col, want in (
+        ("geographic_level", geographic_level),
+        ("establishment_type_group", "All state-funded"),
+        ("breakdown_topic", "Total"),
+        ("breakdown", "Total"),
+    ):
+        if col in df.columns:
+            df = df[df[col].str.strip().str.lower() == want.lower()]
+    return df
+
+
+def headline_record(row: pd.Series, keys: tuple[str, ...]) -> dict[str, str]:
+    """A Singer record: the identifying columns, then the headline measures."""
+    record = {key: str(row.get(key, "")).strip() for key in keys}
+    for csv_col, field in KS4_HEADLINE_COL_MAP.items():
+        record[field] = str(row.get(csv_col, "")).strip()
+    return record

pipeline/plugins/extractors/tap-uk-ees/tap_uk_ees/release_precedence.py

@@ -0,0 +1,59 @@
+"""Which release a row comes from when DfE re-publishes a year.
+
+DfE re-publishes earlier years inside later releases: the 2024/25 KS4 results
+file holds 2022/23, 2023/24 and 2024/25. The 2023/24 release's own file,
+re-issued on 10 March 2026 under older column names, was read after it and
+overwrote every 2023/24 row with blanks (audit C2). A stream that opts in
+treats the newest release as the authority for every year it contains.
+
+Free of the Singer SDK so CI's pytest, which installs only the backend's
+requirements, can load it.
+"""
+from __future__ import annotations
+
+import re
+
+import pandas as pd
+
+_SLUG_YEAR = re.compile(r"^(\d{4})-(\d{2})(?:-|$)")
+
+
+def slug_to_time_period(slug: str) -> str | None:
+    """A release slug's academic year as a time_period: '2022-23' → '202223'.
+
+    Suffixed slugs ('2024-25-revised', '2025-26-provisional') give the same
+    year, so newest_first places them by year; read as unknown, a revised
+    release went last and lost its year to the first release.
+    """
+    match = _SLUG_YEAR.match(slug or "")
+    return match.group(1) + match.group(2) if match else None
+
+
+def newest_first(releases: list[dict]) -> list[dict]:
+    """Releases by time_period, newest first. A release whose time_period is
+    unknown goes last, in the order given."""
+    dated = [r for r in releases if r.get("time_period")]
+    undated = [r for r in releases if not r.get("time_period")]
+    return sorted(dated, key=lambda r: r["time_period"], reverse=True) + undated
+
+
+def periods_in(df: pd.DataFrame) -> set[str]:
+    """The years a release's rows cover."""
+    if "time_period" not in df.columns:
+        return set()
+    return set(df["time_period"].astype(str).str.strip()) - {""}
+
+
+def drop_owned_periods(
+    df: pd.DataFrame, owned: set[str]
+) -> tuple[pd.DataFrame, dict[str, int]]:
+    """Drop the rows for years a newer release already supplied.
+
+    Returns the rows kept and, for each year dropped, how many rows went.
+    """
+    if "time_period" not in df.columns or not owned:
+        return df, {}
+    periods = df["time_period"].astype(str).str.strip()
+    dropped = periods.isin(owned)
+    skipped = {str(k): int(v) for k, v in periods[dropped].value_counts().items()}
+    return df[~dropped], skipped

pipeline/plugins/extractors/tap-uk-ees/tap_uk_ees/tap.py

@@ -17,6 +17,20 @@ import requests
 from singer_sdk import Stream, Tap
 from singer_sdk import typing as th
 
+from tap_uk_ees.ks4_info import KS4_INFO_FIELDS, KS4_INFO_RENAMES
+from tap_uk_ees.ks4_summary import (
+    KS4_HEADLINE_COL_MAP,
+    KS4_SUMMARY_CSV_URL,
+    headline_record,
+    headline_rows,
+)
+from tap_uk_ees.release_precedence import (
+    drop_owned_periods,
+    newest_first,
+    periods_in,
+    slug_to_time_period,
+)
+
 CONTENT_API_BASE = (
     "https://content.explore-education-statistics.service.gov.uk/api"
 )
@@ -31,14 +45,6 @@ def get_content_release_id(publication_slug: str) -> str:
     return resp.json()["id"]
 
 
-def _slug_to_time_period(slug: str) -> str | None:
-    """Convert a release slug like '2022-23' to a time_period like '202223'."""
-    parts = slug.split("-")
-    if len(parts) == 2 and len(parts[0]) == 4 and len(parts[1]) == 2:
-        return parts[0] + parts[1]
-    return None
-
-
 def get_all_releases(publication_slug: str) -> list[dict]:
     """Return all releases for a publication as dicts with 'id' and 'time_period'.
 
@@ -63,7 +69,7 @@ def get_all_releases(publication_slug: str) -> list[dict]:
             total_pages = paging.get("totalPages", 1)
 
         for r in releases:
-            time_period = _slug_to_time_period(r.get("slug", ""))
+            time_period = slug_to_time_period(r.get("slug", ""))
             result.append({"id": r["id"], "time_period": time_period})
 
         if page >= total_pages:
@@ -88,6 +94,8 @@ class EESDatasetStream(Stream):
     target CSV path inside the ZIP (substring match, not exact).
     Subclasses may set _column_renames to map messy CSV column names to
     clean Singer field names before yielding records.
+    Subclasses may set _newest_release_owns_period when DfE re-publishes
+    earlier years in later releases and the newest copy is the authority.
     """
 
     replication_key = None
@@ -96,6 +104,7 @@ class EESDatasetStream(Stream):
     _urn_column: str = "school_urn"  # column name for URN in the CSV
     _encoding: str = "utf-8"  # CSV file encoding (some DfE files use latin-1)
     _column_renames: dict = {}  # CSV column name → Singer field name
+    _newest_release_owns_period: bool = False  # see release_precedence.py
 
     def get_records(self, context):
         import pandas as pd
@@ -110,6 +119,9 @@ class EESDatasetStream(Stream):
         self.logger.info(
             "Found %d release(s) for %s", len(releases), self._publication_slug
         )
+        if self._newest_release_owns_period:
+            releases = newest_first(releases)
+        owned_periods: set[str] = set()
 
         for release in releases:
             release_id = release["id"]
@@ -163,6 +175,15 @@ class EESDatasetStream(Stream):
             if urn_col in df.columns:
                 df = df[df[urn_col].notna() & (df[urn_col] != "")]
 
+            if self._newest_release_owns_period:
+                df, skipped = drop_owned_periods(df, owned_periods)
+                for period, count in sorted(skipped.items()):
+                    self.logger.info(
+                        "Skipping %d rows for %s from release %s: a newer release supplied that year",
+                        count, period, release_id,
+                    )
+                owned_periods |= periods_in(df)
+
             self.logger.info("Emitting %d school-level rows from release %s", len(df), release_id)
 
             for _, row in df.iterrows():
@@ -251,6 +272,9 @@ class EESKS4PerformanceStream(EESDatasetStream):
     primary_keys = ["school_urn", "time_period", "breakdown_topic", "breakdown", "sex"]
     _publication_slug = "key-stage-4-performance"
     _target_filename = "performance_tables_schools"
+    # DfE's 2024/25 file re-publishes 2022/23 and 2023/24 under current names;
+    # the 2023/24 release's own file uses older ones (audit C2).
+    _newest_release_owns_period = True
     schema = th.PropertiesList(
         th.Property("time_period", th.StringType, required=True),
         th.Property("school_urn", th.StringType, required=True),
@@ -310,34 +334,20 @@ class EESKS4PerformanceStream(EESDatasetStream):
 
 
 # ── KS4 Information (wide format: one row per school, context/demographics) ──
-# File: 202425_information_about_schools_provisional.csv (38 cols)
+# Files: 202425_information_about_schools_final.csv (38 cols, current names);
+# 202324_information_about_schools_final.csv (60 cols, older names — the only
+# source of 2023/24 information). Field list and renames: ks4_info.py.
 
 class EESKS4InfoStream(EESDatasetStream):
     name = "ees_ks4_info"
     primary_keys = ["school_urn", "time_period"]
     _publication_slug = "key-stage-4-performance"
     _target_filename = "information_about_schools"
+    _column_renames = KS4_INFO_RENAMES
     schema = th.PropertiesList(
         th.Property("time_period", th.StringType, required=True),
         th.Property("school_urn", th.StringType, required=True),
-        th.Property("school_laestab", th.StringType),
-        th.Property("school_name", th.StringType),
-        th.Property("establishment_type_group", th.StringType),
-        th.Property("reldenom", th.StringType),
-        th.Property("admpol_pt", th.StringType),
-        th.Property("egender", th.StringType),
-        th.Property("agerange", th.StringType),
-        th.Property("allks_pupil_count", th.StringType),
-        th.Property("allks_boys_count", th.StringType),
-        th.Property("allks_girls_count", th.StringType),
-        th.Property("endks4_pupil_count", th.StringType),
-        th.Property("ks2_scaledscore_average", th.StringType),
-        th.Property("sen_with_ehcp_pupil_percent", th.StringType),
-        th.Property("sen_pupil_percent", th.StringType),
-        th.Property("sen_no_ehcp_pupil_percent", th.StringType),
-        th.Property("attainment8_diffn", th.StringType),
-        th.Property("progress8_diffn", th.StringType),
-        th.Property("progress8_banding", th.StringType),
+        *[th.Property(field, th.StringType) for field in KS4_INFO_FIELDS],
     ).to_dict()
 
 
@@ -564,37 +574,23 @@ class EESKs2NationalStream(Stream):
             yield record
 
 
-# ── KS4 National Headlines (national level only — one row per year) ──────────
-# Dataset: "National characteristics summary data" (Key stage 4 performance).
-# Official England state-funded headline measures, 2018/19 → latest.
-# Suppressed values ('z', 'x') → NULL downstream. Progress 8 is legitimately
-# absent in years with no KS2 baseline (e.g. 2024/25) — that is DfE policy,
-# not missing data.
+# ── KS4 National and LA Headlines (one data set, two streams) ────────────────
+# DfE's "summary, all state-funded" data set: England, regional and LA rows,
+# 2018/19 → latest. URL, measures and filters: ks4_summary.py.
 
-_KS4_NATIONAL_CSV_URL = (
-    "https://explore-education-statistics.service.gov.uk/data-catalogue/"
-    "data-set/1b649e16-01e8-435b-a814-56be2faf9054/csv"
-)
+def _read_ks4_summary(logger):
+    """Download DfE's KS4 summary data set."""
+    import pandas as pd
 
-_KS4_NATIONAL_COL_MAP = {
-    "attainment8_average":    "attainment_8_score",
-    "progress8_average":      "progress_8_score",
-    "engmath_94_percent":     "english_maths_standard_pass_pct",
-    "engmath_95_percent":     "english_maths_strong_pass_pct",
-    "ebacc_entering_percent": "ebacc_entry_pct",
-    "ebacc_94_percent":       "ebacc_standard_pass_pct",
-    "ebacc_95_percent":       "ebacc_strong_pass_pct",
-    "ebacc_aps_average":      "ebacc_avg_score",
-}
+    logger.info("Downloading KS4 summary data set: %s", KS4_SUMMARY_CSV_URL)
+    resp = requests.get(KS4_SUMMARY_CSV_URL, timeout=60)
+    resp.raise_for_status()
+    return pd.read_csv(io.BytesIO(resp.content), dtype=str, keep_default_na=False)
 
 
 class EESKs4NationalStream(Stream):
-    """National KS4 headline averages — one row per academic year.
-
-    Filters to geographic_level == 'National', establishment_type_group ==
-    'All state-funded', breakdown_topic == 'Total', breakdown == 'Total'
-    so only the England-wide all-pupils row per year is emitted.
-    """
+    """National KS4 headline averages — one row per academic year (England,
+    all state-funded schools, all pupils)."""
 
     name = "ees_ks4_national"
     primary_keys = ["time_period"]
@@ -602,34 +598,41 @@ class EESKs4NationalStream(Stream):
 
     schema = th.PropertiesList(
         th.Property("time_period", th.StringType, required=True),
-        *[th.Property(out, th.StringType) for out in _KS4_NATIONAL_COL_MAP.values()],
+        *[th.Property(out, th.StringType) for out in KS4_HEADLINE_COL_MAP.values()],
     ).to_dict()
 
     def get_records(self, context):
-        import pandas as pd
-
-        self.logger.info("Downloading KS4 national headlines: %s", _KS4_NATIONAL_CSV_URL)
-        resp = requests.get(_KS4_NATIONAL_CSV_URL, timeout=60)
-        resp.raise_for_status()
-
-        df = pd.read_csv(io.BytesIO(resp.content), dtype=str, keep_default_na=False)
-        df.columns = [c.strip().lower() for c in df.columns]
-
-        for col, want in [
-            ("geographic_level", "national"),
-            ("establishment_type_group", "all state-funded"),
-            ("breakdown_topic", "total"),
-            ("breakdown", "total"),
-        ]:
-            if col in df.columns:
-                df = df[df[col].str.strip().str.lower() == want]
-
+        df = headline_rows(_read_ks4_summary(self.logger), "National")
         self.logger.info("Emitting %d national KS4 rows", len(df))
         for _, row in df.iterrows():
-            record = {"time_period": row.get("time_period", "").strip()}
-            for csv_col, field in _KS4_NATIONAL_COL_MAP.items():
-                record[field] = row.get(csv_col, "").strip()
-            yield record
+            yield headline_record(row, ("time_period",))
+
+
+class EESKs4LaStream(Stream):
+    """DfE's KS4 local-authority averages — one row per academic year and LA
+    (all state-funded schools, all pupils), from the same data set as
+    ees_ks4_national. They match DfE's published performance-table LA averages
+    and replace a mean the API took over every school, independent and special
+    included (audit H2). old_la_code is the GIAS LA code: schools join on it,
+    not on the name."""
+
+    name = "ees_ks4_la"
+    primary_keys = ["time_period", "old_la_code"]
+    replication_key = None
+
+    schema = th.PropertiesList(
+        th.Property("time_period", th.StringType, required=True),
+        th.Property("old_la_code", th.StringType, required=True),
+        th.Property("new_la_code", th.StringType),
+        th.Property("la_name", th.StringType),
+        *[th.Property(out, th.StringType) for out in KS4_HEADLINE_COL_MAP.values()],
+    ).to_dict()
+
+    def get_records(self, context):
+        df = headline_rows(_read_ks4_summary(self.logger), "Local authority")
+        self.logger.info("Emitting %d LA KS4 rows", len(df))
+        for _, row in df.iterrows():
+            yield headline_record(row, ("time_period", "old_la_code", "new_la_code", "la_name"))
 
 
 # ── Legacy KS2 (pre-COVID wide format from DfE performance tables) ────────────
@@ -972,6 +975,7 @@ class TapUKEES(Tap):
             LegacyKS4Stream(self),
             EESKs2NationalStream(self),
             EESKs4NationalStream(self),
+            EESKs4LaStream(self),
         ]
 
 

pipeline/plugins/extractors/tap-uk-gias/tap_uk_gias/gias_csv.py

@@ -0,0 +1,26 @@
+"""Read a GIAS extract from the raw bytes of the download.
+
+GIAS writes its CSVs in Windows-1252 and sends no charset, so `resp.text`
+leaves requests to guess the codec. On 3 Oct 2026 it guessed windows-1250 and
+"à" became "ŕ". Decode the bytes ourselves instead.
+"""
+
+from __future__ import annotations
+
+import io
+
+import pandas as pd
+
+GIAS_ENCODING = "cp1252"
+
+
+def read_gias_csv(content: bytes, logger=None) -> pd.DataFrame:
+    """Every column as a string; a blank cell stays ''."""
+    # Windows-1252 leaves five bytes undefined. One stray byte must not stop
+    # the daily refresh of every school, so it becomes U+FFFD and is logged.
+    text = content.decode(GIAS_ENCODING, errors="replace")
+    undecodable = text.count("�")
+    if undecodable and logger is not None:
+        logger.warning("%d byte(s) in the GIAS extract could not be decoded as %s",
+                       undecodable, GIAS_ENCODING)
+    return pd.read_csv(io.StringIO(text), dtype=str, keep_default_na=False)

pipeline/plugins/extractors/tap-uk-gias/tap_uk_gias/tap.py

@@ -7,6 +7,8 @@ from datetime import date, timedelta
 from singer_sdk import Stream, Tap
 from singer_sdk import typing as th
 
+from tap_uk_gias.gias_csv import read_gias_csv
+
 GIAS_URL_TEMPLATE = (
     "https://ea-edubase-api-prod.azurewebsites.net"
     "/edubase/downloads/public/edubasealldata{date}.csv"
@@ -74,9 +76,6 @@ class GIASEstablishmentsStream(Stream):
 
     def get_records(self, context):
         """Download GIAS CSV and yield rows."""
-        import io
-
-        import pandas as pd
         import requests
 
         today = date.today()
@@ -94,12 +93,7 @@ class GIASEstablishmentsStream(Stream):
 
         resp.raise_for_status()
 
-        df = pd.read_csv(
-            io.StringIO(resp.text),
-            encoding="latin-1",
-            dtype=str,
-            keep_default_na=False,
-        )
+        df = read_gias_csv(resp.content, self.logger)
 
         for _, row in df.iterrows():
             record = row.to_dict()
@@ -126,9 +120,6 @@ class GIASLinksStream(Stream):
 
     def get_records(self, context):
         """Download GIAS links CSV and yield rows."""
-        import io
-
-        import pandas as pd
         import requests
 
         today = date.today()
@@ -146,12 +137,7 @@ class GIASLinksStream(Stream):
 
         resp.raise_for_status()
 
-        df = pd.read_csv(
-            io.StringIO(resp.text),
-            encoding="latin-1",
-            dtype=str,
-            keep_default_na=False,
-        )
+        df = read_gias_csv(resp.content, self.logger)
 
         for _, row in df.iterrows():
             record = row.to_dict()

pipeline/tests/test_dag_selectors.py

@@ -0,0 +1,98 @@
+"""Every scheduled dbt build must only build models whose parents exist.
+
+The daily GIAS build selects `stg_gias_establishments+`, so any mart that joins
+dim_school joins the daily build too. When such a mart also reads a staging
+model that only the manually triggered EES DAG builds, the daily build fails in
+any database where that DAG has not run since. Sync and cache invalidation then
+never run either. The destinations marts did this from late August 2026.
+
+The graph is read from the model SQL, because CI has no dbt.
+"""
+import re
+from collections import defaultdict
+from pathlib import Path
+
+import pytest
+
+PIPELINE = Path(__file__).resolve().parents[1]
+MODELS = PIPELINE / 'transform' / 'models'
+DAG_FILE = PIPELINE / 'dags' / 'school_data_pipeline.py'
+
+REF = re.compile(r"ref\(\s*'([a-z0-9_]+)'\s*\)")
+DBT_BUILD = re.compile(r'dbt_build\w*\s*=\s*BashOperator\(.*?build --profiles-dir \. --target production ([^"]+)"', re.S)
+DAG_ID = re.compile(r'dag_id="([a-z0-9_]+)"')
+
+DAILY = 'school_data_daily'
+
+# dim_school reads int_ofsted_latest only when the relation exists
+# (adapter.get_relation), so a missing table is not a failure.
+OPTIONAL_PARENTS = {'int_ofsted_latest'}
+
+
+def model_parents():
+    """{model: models it refs}. Seeds are left out: they are loaded once and always exist."""
+    sql = {p.stem: p.read_text() for p in MODELS.rglob('*.sql')}
+    return {name: set(REF.findall(text)) & set(sql) for name, text in sql.items()}
+
+
+def downstream(node, children):
+    seen, stack = {node}, [node]
+    while stack:
+        for child in children[stack.pop()]:
+            if child not in seen:
+                seen.add(child)
+                stack.append(child)
+    return seen
+
+
+def expand(tokens, children):
+    out = set()
+    for token in tokens:
+        out |= downstream(token[:-1], children) if token.endswith('+') else {token}
+    return out
+
+
+def scheduled_builds():
+    """{dag_id: dbt selection arguments} for every dbt build in the DAG file."""
+    text = DAG_FILE.read_text()
+    starts = [(m.start(), m.group(1)) for m in DAG_ID.finditer(text)]
+    builds = {}
+    for i, (start, dag_id) in enumerate(starts):
+        end = starts[i + 1][0] if i + 1 < len(starts) else len(text)
+        found = DBT_BUILD.search(text, start, end)
+        if found:
+            builds[dag_id] = found.group(1)
+    return builds
+
+
+def selected_models(args, parents):
+    children = defaultdict(set)
+    for model, ps in parents.items():
+        for p in ps:
+            children[p].add(model)
+    select = re.search(r'--select (.+?)(?= --exclude|$)', args).group(1).split()
+    excluded = re.search(r'--exclude (.+)$', args)
+    exclude = excluded.group(1).split() if excluded else []
+    return (expand(select, children) - expand(exclude, children)) & set(parents)
+
+
+PARENTS = model_parents()
+BUILDS = scheduled_builds()
+DAILY_MODELS = selected_models(BUILDS[DAILY], PARENTS)
+
+
+def test_every_dag_with_a_dbt_build_is_parsed():
+    assert set(BUILDS) == {
+        'school_data_daily', 'school_data_monthly_ofsted', 'school_data_annual_ees',
+        'school_data_annual_idaci', 'school_data_annual_distance',
+    }
+
+
+@pytest.mark.parametrize('dag_id', sorted(BUILDS))
+def test_selected_models_only_read_models_that_exist(dag_id):
+    selected = selected_models(BUILDS[dag_id], PARENTS)
+    # The daily build is the base layer: other DAGs may rely on what it builds.
+    available = selected | OPTIONAL_PARENTS | (DAILY_MODELS if dag_id != DAILY else set())
+    missing = {model: sorted(PARENTS[model] - available) for model in sorted(selected)
+               if PARENTS[model] - available}
+    assert missing == {}, f'{dag_id} builds models whose parents it never builds: {missing}'

pipeline/tests/test_ees_ks4_info_names.py

@@ -0,0 +1,67 @@
+"""KS4 school information for 2023/24 exists only in the 2023/24 release,
+whose file uses DfE's older column names. The stream declared only the newer
+ones, so every 2023/24 field loaded as null (audit C2). The headers below are
+DfE's, copied from 202324_information_about_schools_final.csv and
+202425_information_about_schools_final.csv.
+"""
+import importlib.util
+from pathlib import Path
+
+import pytest
+
+MODULE = (Path(__file__).resolve().parents[1] / 'plugins' / 'extractors' / 'tap-uk-ees'
+          / 'tap_uk_ees' / 'ks4_info.py')
+
+HEADER_2023_24 = (
+    'time_period', 'time_identifier', 'geographic_level', 'country_code', 'country_name',
+    'school_laestab', 'school_urn', 'school_name', 'old_la_code', 'new_la_code', 'la_name',
+    'version', 'establishment_type_group', 'full_address', 'telnum', 'pcon_code', 'pcon_name',
+    'contflag', 'iclose', 'reldenom', 'admpol_pt', 'egender', 'feeder', 'agerange',
+    't_allks_pupils', 't_allks_boys', 't_allks_girls', 't_pupils', 't_boys', 'pt_boys',
+    't_girls', 'pt_girls', 'avg_ks2_scaledscore', 't_prior_lo', 'pt_prior_lo', 't_prior_av',
+    'pt_prior_av', 't_prior_hi', 'pt_prior_hi', 't_disadvantaged', 'pt_disadvantaged',
+    't_not_disadvantaged', 'pt_not_disadvantaged', 't_language_not_english',
+    'pt_language_not_english', 't_language_english', 'pt_language_english',
+    't_language_unknown', 'pt_language_unknown', 't_not_mobile', 'pt_not_mobile',
+    't_sen_with_ehcp', 'pt_sen_with_ehcp', 't_sen', 'pt_sen', 't_sen_no_ehcp',
+    'pt_sen_no_ehcp', 'diffn_att8', 'diffn_p8mea', 'p8_banding',
+)
+
+HEADER_2024_25 = (
+    'time_period', 'time_identifier', 'geographic_level', 'country_code', 'country_name',
+    'school_laestab', 'school_urn', 'school_name', 'old_la_code', 'new_la_code', 'la_name',
+    'version', 'establishment_type_group', 'full_address', 'telnum', 'pcon_code', 'pcon_name',
+    'contflag', 'iclose', 'reldenom', 'admpol_pt', 'egender', 'feeder', 'agerange',
+    'allks_pupil_count', 'allks_boys_count', 'allks_girls_count', 'endks4_pupil_count',
+    'ks2_scaledscore_average', 'sen_with_ehcp_pupil_count', 'sen_with_ehcp_pupil_percent',
+    'sen_pupil_count', 'sen_pupil_percent', 'sen_no_ehcp_pupil_count',
+    'sen_no_ehcp_pupil_percent', 'attainment8_diffn', 'progress8_diffn', 'progress8_banding',
+)
+
+
+@pytest.fixture
+def ks4_info():
+    spec = importlib.util.spec_from_file_location('ks4_info', MODULE)
+    module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(module)
+    return module
+
+
+def test_every_declared_field_is_in_the_2023_24_file_once_renamed(ks4_info):
+    renamed = {ks4_info.KS4_INFO_RENAMES.get(c, c) for c in HEADER_2023_24}
+    assert set(ks4_info.KS4_INFO_FIELDS) - renamed == set()
+
+
+def test_every_declared_field_is_in_the_2024_25_file(ks4_info):
+    assert set(ks4_info.KS4_INFO_FIELDS) - set(HEADER_2024_25) == set()
+
+
+def test_the_renames_cannot_collide_with_either_file(ks4_info):
+    # An old name in the current file, or a new name already in the old file,
+    # would let a rename overwrite a real column.
+    assert set(ks4_info.KS4_INFO_RENAMES) & set(HEADER_2024_25) == set()
+    assert set(ks4_info.KS4_INFO_RENAMES.values()) & set(HEADER_2023_24) == set()
+
+
+def test_every_rename_names_a_declared_field(ks4_info):
+    assert set(ks4_info.KS4_INFO_RENAMES.values()) <= set(ks4_info.KS4_INFO_FIELDS)

pipeline/tests/test_ees_ks4_summary.py

@@ -0,0 +1,72 @@
+"""DfE's KS4 "summary, all state-funded" data set holds England, regional and
+LA rows. The England stream kept only the England row; its LA rows match
+DfE's published LA averages exactly, where the API's own mean was 7 points
+low (audit H2). Values below are DfE's for Kensington and Chelsea (207) and
+Wandsworth (212).
+"""
+import importlib.util
+import io
+from pathlib import Path
+
+import pandas as pd
+import pytest
+
+MODULE = (Path(__file__).resolve().parents[1] / 'plugins' / 'extractors' / 'tap-uk-ees'
+          / 'tap_uk_ees' / 'ks4_summary.py')
+
+CSV = """time_period,geographic_level,old_la_code,new_la_code,la_name,establishment_type_group,breakdown_topic,breakdown,attainment8_average,progress8_average,engmath_94_percent,engmath_95_percent,ebacc_entering_percent,ebacc_94_percent,ebacc_95_percent,ebacc_aps_average
+202425,National,,,,All state-funded,Total,Total,46.1,z,64.5,45.7,40.5,26.9,17.7,4.1
+202425,National,,,,All state-funded,Sex,Boys,44.1,z,62.0,43.0,38.0,24.0,16.0,3.9
+202425,Regional,,,,All state-funded,Total,Total,47.2,z,66.0,47.0,41.0,28.0,18.0,4.2
+202425,Local authority,207,E09000020,Kensington and Chelsea,All state-funded,Total,Total,54.5,z,77,61.4,45.6,32,26.6,4.89
+202425,Local authority,207,E09000020,Kensington and Chelsea,All state-funded,Sex,Girls,57.0,z,80,64.0,48.0,35,28.0,5.1
+202324,Local authority,207,E09000020,Kensington and Chelsea,All state-funded,Total,Total,54.5,0.29,76,60.0,44.0,31,25.0,4.8
+202425,Local authority,212,E09000032,Wandsworth,All state-funded,Total,Total,51.8,z,72,55.0,50.0,33,24.0,4.6
+202425,Local authority,212,E09000032,Wandsworth,Academies and free schools,Total,Total,52.0,z,73,56.0,51.0,34,25.0,4.7
+"""
+
+LA_KEYS = ('time_period', 'old_la_code', 'new_la_code', 'la_name')
+
+
+def _df():
+    return pd.read_csv(io.StringIO(CSV), dtype=str, keep_default_na=False)
+
+
+@pytest.fixture
+def summary():
+    spec = importlib.util.spec_from_file_location('ks4_summary', MODULE)
+    module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(module)
+    return module
+
+
+def test_la_rows_are_one_per_la_and_year(summary):
+    rows = summary.headline_rows(_df(), 'Local authority')
+    assert sorted(zip(rows['time_period'], rows['old_la_code'])) == [
+        ('202324', '207'), ('202425', '207'), ('202425', '212')]
+
+
+def test_an_la_record_carries_codes_name_and_the_headline_measures(summary):
+    rows = summary.headline_rows(_df(), 'Local authority')
+    row = rows[(rows['time_period'] == '202425') & (rows['old_la_code'] == '207')].iloc[0]
+    assert summary.headline_record(row, LA_KEYS) == {
+        'time_period': '202425', 'old_la_code': '207', 'new_la_code': 'E09000020',
+        'la_name': 'Kensington and Chelsea',
+        'attainment_8_score': '54.5', 'progress_8_score': 'z',
+        'english_maths_standard_pass_pct': '77', 'english_maths_strong_pass_pct': '61.4',
+        'ebacc_entry_pct': '45.6', 'ebacc_standard_pass_pct': '32',
+        'ebacc_strong_pass_pct': '26.6', 'ebacc_avg_score': '4.89',
+    }
+
+
+def test_the_england_rows_are_one_per_year(summary):
+    rows = summary.headline_rows(_df(), 'National')
+    assert list(rows['time_period']) == ['202425']
+    assert summary.headline_record(rows.iloc[0], ('time_period',))['attainment_8_score'] == '46.1'
+
+
+def test_column_names_and_labels_match_whatever_their_case(summary):
+    df = _df()
+    df.columns = [c.upper() for c in df.columns]
+    df['GEOGRAPHIC_LEVEL'] = df['GEOGRAPHIC_LEVEL'].str.upper()
+    assert len(summary.headline_rows(df, 'Local authority')) == 3

pipeline/tests/test_ees_release_precedence.py

@@ -0,0 +1,100 @@
+"""DfE re-publishes earlier years inside later KS4 releases.
+
+The 2024/25 results file holds 2022/23, 2023/24 and 2024/25 under current
+column names. The 2023/24 release's own file, re-issued in March 2026 under
+older names, was read after it and overwrote every 2023/24 row with blanks
+(audit C2). For the KS4 results stream the newest release owns every year it
+contains.
+"""
+import importlib.util
+import re
+from pathlib import Path
+
+import pandas as pd
+import pytest
+
+TAP_DIR = (Path(__file__).resolve().parents[1] / 'plugins' / 'extractors' / 'tap-uk-ees'
+           / 'tap_uk_ees')
+
+
+@pytest.fixture
+def precedence():
+    spec = importlib.util.spec_from_file_location(
+        'release_precedence', TAP_DIR / 'release_precedence.py')
+    module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(module)
+    return module
+
+
+def _release(period):
+    return {'id': f'release-{period}', 'time_period': period}
+
+
+def test_releases_are_taken_newest_first_whatever_order_the_api_gives(precedence):
+    releases = [_release('202223'), _release('202425'), _release(None), _release('202324')]
+    ordered = precedence.newest_first(releases)
+    assert [r['time_period'] for r in ordered] == ['202425', '202324', '202223', None]
+
+
+def test_a_year_a_newer_release_supplied_is_dropped_from_an_older_one(precedence):
+    newer = pd.DataFrame({'time_period': ['202425', '202324', '202223'], 'school_urn': ['1'] * 3})
+    older = pd.DataFrame({'time_period': ['202324', '202324', '201920'], 'school_urn': ['1', '2', '1']})
+
+    kept, skipped = precedence.drop_owned_periods(older, precedence.periods_in(newer))
+
+    assert list(kept['time_period']) == ['201920']
+    assert skipped == {'202324': 2}
+
+
+def test_periods_match_despite_surrounding_spaces(precedence):
+    owned = precedence.periods_in(pd.DataFrame({'time_period': [' 202324 ']}))
+    kept, skipped = precedence.drop_owned_periods(pd.DataFrame({'time_period': ['202324']}), owned)
+    assert owned == {'202324'}
+    assert kept.empty
+    assert skipped == {'202324': 1}
+
+
+def test_nothing_is_dropped_before_any_year_is_owned(precedence):
+    df = pd.DataFrame({'time_period': ['202324'], 'school_urn': ['1']})
+    kept, skipped = precedence.drop_owned_periods(df, set())
+    assert kept.equals(df)
+    assert skipped == {}
+
+
+def test_a_file_without_time_period_is_left_alone(precedence):
+    df = pd.DataFrame({'school_urn': ['1']})
+    kept, skipped = precedence.drop_owned_periods(df, {'202324'})
+    assert kept.equals(df)
+    assert skipped == {}
+    assert precedence.periods_in(df) == set()
+
+
+def test_only_the_ks4_results_stream_opts_in():
+    # A general rule would wipe KS2: the 2024/25 KS2 file holds 98,448 of the
+    # 955,956 rows the 2023/24 release has for 2023/24.
+    source = (TAP_DIR / 'tap.py').read_text()
+    opted_in = [chunk.split('(')[0] for chunk in source.split('\nclass ')[1:]
+                if re.search(r'_newest_release_owns_period\s*=\s*True', chunk)]
+    assert opted_in == ['EESKS4PerformanceStream']
+
+
+@pytest.mark.parametrize('slug, period', [
+    ('2024-25', '202425'),
+    ('2024-25-revised', '202425'),
+    ('2025-26-provisional', '202526'),
+    ('latest', None),
+    ('', None),
+])
+def test_a_release_slug_gives_its_year_whatever_its_suffix(precedence, slug, period):
+    # KS2 already publishes "2024-25-revised" and "2025-26-provisional". An
+    # unread suffix sent the release last, behind the provisional one for the
+    # same year, which then owned the year and dropped every revised row.
+    assert precedence.slug_to_time_period(slug) == period
+
+
+def test_within_a_year_the_api_order_is_kept(precedence):
+    # The API lists a year's revised release before its first release.
+    releases = [{'id': 'revised', 'time_period': '202526'},
+                {'id': 'first', 'time_period': '202526'},
+                {'id': 'older', 'time_period': '202425'}]
+    assert [r['id'] for r in precedence.newest_first(releases)] == ['revised', 'first', 'older']

pipeline/tests/test_gias_encoding.py

@@ -0,0 +1,66 @@
+"""GIAS publishes its extracts in Windows-1252 and declares no charset.
+
+The tap used to hand pandas `resp.text`, so requests guessed the codec.
+On 3 Oct 2026 it guessed windows-1250, and "St Thomas à Becket" was stored
+as "St Thomas ŕ Becket". The `encoding=` passed to read_csv did nothing,
+because the text was already decoded.
+"""
+import importlib.util
+import logging
+from pathlib import Path
+
+import pytest
+
+MODULE = (Path(__file__).resolve().parents[1] / 'plugins' / 'extractors' / 'tap-uk-gias'
+          / 'tap_uk_gias' / 'gias_csv.py')
+
+
+@pytest.fixture
+def gias_csv():
+    spec = importlib.util.spec_from_file_location('gias_csv', MODULE)
+    module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(module)
+    return module
+
+
+# Byte for byte as GIAS writes it: 0xE0 à, 0x92 ’, 0xE9 é, 0xB0 °, 0xE7 ç.
+EXTRACT = (
+    b'"URN","EstablishmentName","HeadLastName"\r\n'
+    b'"138950","St Thomas \xe0 Becket Catholic Secondary School","Smith"\r\n'
+    b'"100000","The Dean and Chapter of St Paul\x92s Cathedral","Pr\xe9vert"\r\n'
+    b'"140677","North Star 180\xb0","Fran\xe7ois"\r\n'
+    b'"100001","No head recorded",""\r\n'
+)
+
+
+def test_names_decode_as_windows_1252(gias_csv):
+    df = gias_csv.read_gias_csv(EXTRACT)
+    assert list(df['EstablishmentName']) == [
+        'St Thomas à Becket Catholic Secondary School',
+        'The Dean and Chapter of St Paul’s Cathedral',
+        'North Star 180°',
+        'No head recorded',
+    ]
+    assert list(df['HeadLastName']) == ['Smith', 'Prévert', 'François', '']
+
+
+def test_the_codec_requests_guessed_is_not_used(gias_csv):
+    # What the tap stored on 3 Oct: the same bytes read as windows-1250.
+    assert 'ŕ' in EXTRACT.decode('cp1250')
+    names = ' '.join(gias_csv.read_gias_csv(EXTRACT)['EstablishmentName'])
+    assert 'ŕ' not in names
+
+
+def test_values_stay_strings(gias_csv):
+    df = gias_csv.read_gias_csv(EXTRACT)
+    assert df.loc[0, 'URN'] == '138950'
+
+
+def test_a_byte_windows_1252_leaves_undefined_does_not_stop_the_load(gias_csv, caplog):
+    # 0x81 has no Windows-1252 character. One odd name must not block the daily
+    # refresh of every school, but it must be visible in the log.
+    extract = b'"URN","EstablishmentName"\r\n"100002","Odd \x81 Name"\r\n'
+    with caplog.at_level(logging.WARNING):
+        df = gias_csv.read_gias_csv(extract, logger=logging.getLogger('gias'))
+    assert df.loc[0, 'EstablishmentName'] == 'Odd � Name'
+    assert 'could not be decoded' in caplog.text

pipeline/transform/macros/safe_numeric.sql

@@ -3,7 +3,9 @@
   Casts a string column to numeric, treating any non-numeric value as NULL.
   Handles all EES suppression codes (z, c, x, q, u, etc.) without needing
   an explicit list — any string that doesn't look like a number becomes NULL.
+  A trailing percent sign is accepted: DfE's 2023/24 KS2 information file
+  writes percentages as "34%" (audit C2).
 #}
 {% macro safe_numeric(col) -%}
-    CASE WHEN {{ col }} ~ '^-?[0-9]+(\.[0-9]+)?$' THEN {{ col }}::numeric ELSE NULL END
+    CASE WHEN {{ col }} ~ '^-?[0-9]+(\.[0-9]+)?%?$' THEN rtrim({{ col }}, '%')::numeric ELSE NULL END
 {%- endmacro %}

pipeline/transform/models/intermediate/int_ofsted_latest.sql

@@ -1,18 +1,91 @@
--- Intermediate model: Latest Ofsted inspection per URN
--- Picks the most recent inspection for each school
+-- Intermediate model: the current Ofsted status per URN
+-- One row per school: its latest visit (report card, graded or ungraded
+-- inspection) and the overall grade still in force, if any. A grade is dated
+-- by the inspection that awarded or confirmed it, never by a later visit.
+-- Rule and examples: docs/superpowers/specs/2026-10-05-ofsted-current-status-design.md
 
-with ranked as (
+with inspections as (
     select
         *,
+        -- The newest of the three inspections, read from the dates. (Report
+        -- cards began in Nov 2025, after the last legacy inspections, so today
+        -- a report card is always the latest; nothing below relies on that.)
+        greatest(rc_inspection_date, graded_inspection_date, ungraded_inspection_date)
+            as latest_visit_date
+    from {{ ref('stg_ofsted_inspections') }}
+),
+
+ranked as (
+    select
+        *,
+        -- Monthly loads can leave several rows per school. The newest visit
+        -- wins; the tie-breaks keep the choice deterministic.
         row_number() over (
             partition by urn
-            order by inspection_date desc
+            order by latest_visit_date desc,
+                     rc_inspection_date desc nulls last,
+                     graded_inspection_date desc nulls last,
+                     ungraded_inspection_date desc nulls last
         ) as rn
-    from {{ ref('stg_ofsted_inspections') }}
+    from inspections
+),
+
+latest as (
+    select
+        *,
+        -- Same-day ties resolve report card, then graded, then ungraded.
+        case
+            when rc_inspection_date = latest_visit_date then 'report_card'
+            when graded_inspection_date = latest_visit_date then 'graded'
+            else 'ungraded'
+        end as latest_visit_kind
+    from ranked
+    where rn = 1
+),
+
+graded as (
+    select
+        *,
+        -- The grade still in force. A report card replaced overall grades, so
+        -- none survives it. Otherwise: a graded inspection's own overall grade
+        -- (1-4; "Not judged" and the sentinel 9 are no grade); else an
+        -- ungraded visit's "School remains X"; else, after an ungraded visit
+        -- that names no grade, the graded inspection's grade.
+        case
+            when rc_inspection_date is not null
+                then null
+            when latest_visit_kind = 'graded' and overall_effectiveness between 1 and 4
+                then 'graded_latest'
+            when latest_visit_kind = 'ungraded' and ungraded_grade is not null
+                then 'confirmed'
+            when latest_visit_kind = 'ungraded' and overall_effectiveness between 1 and 4
+                then 'graded_earlier'
+        end as grade_case
+    from latest
 )
 
 select
     urn,
+    latest_visit_date,
+    latest_visit_kind,
+    case when latest_visit_kind = 'ungraded' then ungraded_outcome end as latest_visit_outcome,
+    case grade_case
+        when 'confirmed' then ungraded_grade
+        when 'graded_latest' then overall_effectiveness
+        when 'graded_earlier' then overall_effectiveness
+    end as current_grade,
+    case grade_case
+        when 'confirmed' then ungraded_inspection_date
+        when 'graded_latest' then graded_inspection_date
+        when 'graded_earlier' then graded_inspection_date
+    end as current_grade_date,
+    case grade_case
+        when 'confirmed' then 'confirmed'
+        when 'graded_latest' then 'graded'
+        when 'graded_earlier' then 'graded'
+    end as current_grade_basis,
+    graded_inspection_date,
+    ungraded_inspection_date,
     inspection_date,
     inspection_type,
     framework,
@@ -36,5 +109,4 @@ select
     rc_sixth_form,
     rc_inspection_date,
     report_url
-from ranked
-where rn = 1
+from graded

pipeline/transform/models/intermediate/int_ofsted_latest.yml

@@ -0,0 +1,113 @@
+version: 2
+
+unit_tests:
+  - name: graded_not_judged_has_no_grade
+    description: Rabbsfarm (102408). The 2025 inspection gave no overall grade, so the 2020 "remains Good" is not carried forward (audit C1).
+    model: int_ofsted_latest
+    given:
+      - input: ref('stg_ofsted_inspections')
+        rows:
+          - {urn: 102408, graded_inspection_date: '2025-06-17', ungraded_inspection_date: '2020-02-06', overall_effectiveness: null, ungraded_grade: 2, ungraded_outcome: 'School remains Good'}
+    expect:
+      rows:
+        - {urn: 102408, latest_visit_date: '2025-06-17', latest_visit_kind: graded, latest_visit_outcome: null, current_grade: null, current_grade_date: null, current_grade_basis: null}
+
+  - name: graded_with_overall_grade
+    model: int_ofsted_latest
+    given:
+      - input: ref('stg_ofsted_inspections')
+        rows:
+          - {urn: 1, graded_inspection_date: '2019-06-01', overall_effectiveness: 2}
+    expect:
+      rows:
+        - {urn: 1, latest_visit_date: '2019-06-01', latest_visit_kind: graded, current_grade: 2, current_grade_date: '2019-06-01', current_grade_basis: graded}
+
+  - name: ungraded_remains_good_confirms_the_grade
+    description: Robins Lane (104762). Graded Good 2020, "School remains Good" July 2024 — Good, dated by the confirming visit.
+    model: int_ofsted_latest
+    given:
+      - input: ref('stg_ofsted_inspections')
+        rows:
+          - {urn: 104762, graded_inspection_date: '2020-01-07', ungraded_inspection_date: '2024-07-18', overall_effectiveness: 2, ungraded_grade: 2, ungraded_outcome: 'School remains Good'}
+    expect:
+      rows:
+        - {urn: 104762, latest_visit_date: '2024-07-18', latest_visit_kind: ungraded, latest_visit_outcome: 'School remains Good', current_grade: 2, current_grade_date: '2024-07-18', current_grade_basis: confirmed}
+
+  - name: post_2024_ungraded_keeps_graded_grade_with_its_own_date
+    description: Washwood Heath (139888). Graded Good 2020, "Standards maintained" May 2025 — Good, dated 2020; latest visit May 2025 (audit M1).
+    model: int_ofsted_latest
+    given:
+      - input: ref('stg_ofsted_inspections')
+        rows:
+          - {urn: 139888, graded_inspection_date: '2020-03-03', ungraded_inspection_date: '2025-05-21', overall_effectiveness: 2, ungraded_grade: null, ungraded_outcome: 'Standards maintained'}
+    expect:
+      rows:
+        - {urn: 139888, latest_visit_date: '2025-05-21', latest_visit_kind: ungraded, latest_visit_outcome: 'Standards maintained', current_grade: 2, current_grade_date: '2020-03-03', current_grade_basis: graded}
+
+  - name: ungraded_only_standards_maintained
+    description: Oakgrove (136454). Only an ungraded visit, outcome names no grade.
+    model: int_ofsted_latest
+    given:
+      - input: ref('stg_ofsted_inspections')
+        rows:
+          - {urn: 136454, ungraded_inspection_date: '2024-11-13', ungraded_grade: null, ungraded_outcome: 'Standards maintained'}
+    expect:
+      rows:
+        - {urn: 136454, latest_visit_date: '2024-11-13', latest_visit_kind: ungraded, latest_visit_outcome: 'Standards maintained', current_grade: null, current_grade_date: null, current_grade_basis: null}
+
+  - name: report_card_wins
+    description: The Willink School (110048). A report card is the latest visit and no legacy grade stays in force.
+    model: int_ofsted_latest
+    given:
+      - input: ref('stg_ofsted_inspections')
+        rows:
+          - {urn: 110048, ungraded_inspection_date: '2023-10-05', ungraded_grade: 2, ungraded_outcome: 'School remains Good', rc_inspection_date: '2026-05-06', rc_inclusion: 3}
+    expect:
+      rows:
+        - {urn: 110048, latest_visit_date: '2026-05-06', latest_visit_kind: report_card, latest_visit_outcome: null, current_grade: null, current_grade_date: null, current_grade_basis: null}
+
+  - name: duplicate_rows_newer_report_card_wins
+    description: Monthly loads can leave an older row beside a newer one for the same graded date; the row with the report card must win (audit H3).
+    model: int_ofsted_latest
+    given:
+      - input: ref('stg_ofsted_inspections')
+        rows:
+          - {urn: 138186, graded_inspection_date: '2023-06-13', overall_effectiveness: 3}
+          - {urn: 138186, graded_inspection_date: '2023-06-13', overall_effectiveness: 3, rc_inspection_date: '2026-06-02', rc_inclusion: 3}
+    expect:
+      rows:
+        - {urn: 138186, latest_visit_date: '2026-06-02', latest_visit_kind: report_card, current_grade: null}
+
+  - name: same_day_graded_wins
+    model: int_ofsted_latest
+    given:
+      - input: ref('stg_ofsted_inspections')
+        rows:
+          - {urn: 2, graded_inspection_date: '2024-03-01', ungraded_inspection_date: '2024-03-01', overall_effectiveness: 1, ungraded_grade: 2, ungraded_outcome: 'School remains Good'}
+    expect:
+      rows:
+        - {urn: 2, latest_visit_kind: graded, current_grade: 1, current_grade_basis: graded}
+
+  - name: overall_sentinel_is_not_a_grade
+    model: int_ofsted_latest
+    given:
+      - input: ref('stg_ofsted_inspections')
+        rows:
+          - {urn: 3, graded_inspection_date: '2018-05-01', overall_effectiveness: 9}
+    expect:
+      rows:
+        - {urn: 3, latest_visit_kind: graded, current_grade: null}
+
+  - name: newer_legacy_visit_after_a_report_card
+    description: >
+      Not in Ofsted's data today (0 of 2,451 report-card schools in the 31 Aug
+      2026 MI), but the latest visit is read from the dates, not assumed. The
+      report card still leaves no legacy grade in force.
+    model: int_ofsted_latest
+    given:
+      - input: ref('stg_ofsted_inspections')
+        rows:
+          - {urn: 4, ungraded_inspection_date: '2026-03-02', ungraded_grade: 2, ungraded_outcome: 'School remains Good', rc_inspection_date: '2025-12-01', rc_inclusion: 3}
+    expect:
+      rows:
+        - {urn: 4, latest_visit_date: '2026-03-02', latest_visit_kind: ungraded, latest_visit_outcome: 'School remains Good', current_grade: null, current_grade_date: null, current_grade_basis: null}

pipeline/transform/models/marts/_marts_schema.yml

@@ -125,6 +125,30 @@ models:
       - name: inspection_date
         tests: [not_null]
 
+  - name: fact_ofsted_latest
+    description: >
+      Current Ofsted status, one row per URN: the latest visit and the overall
+      grade still in force. See int_ofsted_latest for the rule.
+    columns:
+      - name: urn
+        tests: [not_null, unique]
+      - name: latest_visit_date
+        tests: [not_null]
+      - name: latest_visit_kind
+        tests:
+          - not_null
+          - accepted_values:
+              values: ['report_card', 'graded', 'ungraded']
+      - name: current_grade
+        tests:
+          - accepted_values:
+              values: [1, 2, 3, 4]
+              quote: false
+      - name: current_grade_basis
+        tests:
+          - accepted_values:
+              values: ['graded', 'confirmed']
+
   - name: fact_pupil_characteristics
     description: Pupil demographics — one row per URN per year
     columns:
@@ -255,11 +279,24 @@ models:
         tests: [not_null, unique]
 
   - name: fact_ks4_national_averages
-    description: Computed national KS4 averages (means across state schools in our dataset — not official DfE figures) — one row per academic year
+    description: Official DfE KS4 national headline averages (England, all state-funded schools, all pupils) — one row per academic year
     columns:
       - name: year
         tests: [not_null, unique]
 
+  - name: fact_ks4_la_averages
+    description: Official DfE KS4 local-authority averages (all state-funded schools, all pupils) — one row per academic year and LA; la_code is the GIAS LA code
+    columns:
+      - name: year
+        tests: [not_null]
+      - name: la_code
+        tests: [not_null]
+      - name: la_name
+        tests: [not_null]
+    tests:
+      - unique:
+          column_name: "year || '-' || la_code"
+
   - name: fact_deprivation
     description: IDACI deprivation index — one row per URN
     columns:

pipeline/transform/models/marts/dim_school.sql

@@ -71,12 +71,12 @@ select
     s.nursery_provision,
     s.admissions_policy_code,
 
-    -- Latest Ofsted (populated after monthly Ofsted pipeline runs)
+    -- Latest Ofsted (populated after monthly Ofsted pipeline runs). The grade
+    -- still in force and the latest visit, from int_ofsted_latest — never a
+    -- grade carried past a newer inspection.
     {% if ofsted_relation is not none %}
-    -- Prefer the graded overall effectiveness; fall back to the grade parsed
-    -- from the latest ungraded (Section 8) outcome when no graded grade exists.
-    coalesce(o.overall_effectiveness, o.ungraded_grade) as ofsted_grade,
-    o.inspection_date as ofsted_date,
+    o.current_grade as ofsted_grade,
+    o.latest_visit_date as ofsted_date,
     o.framework as ofsted_framework
     {% else %}
     null::text as ofsted_grade,

pipeline/transform/models/marts/dim_school.yml

@@ -0,0 +1,35 @@
+version: 2
+
+unit_tests:
+  - name: dim_school_ofsted_grade_is_the_one_still_in_force
+    description: >
+      Rabbsfarm (102408). Its 2025 inspection gave no overall grade, so the 2020
+      "School remains Good" must not reach dim_school (which feeds Typesense's
+      rating), and ofsted_date is the latest visit (audit C1, M1).
+    model: dim_school
+    given:
+      - input: ref('stg_gias_establishments')
+        rows:
+          - {urn: 102408, school_name: 'Rabbsfarm Primary School', status_code: 1, school_type_code: 1, local_authority_code: 312, phase_code: 2}
+      - input: ref('int_ofsted_latest')
+        rows:
+          - {urn: 102408, inspection_date: '2025-06-17', overall_effectiveness: null, ungraded_grade: 2, framework: 'Schools - S5', latest_visit_date: '2025-06-17', current_grade: null}
+    expect:
+      rows:
+        - {urn: 102408, ofsted_grade: null, ofsted_date: '2025-06-17', ofsted_framework: 'Schools - S5'}
+
+  - name: dim_school_ofsted_grade_keeps_its_own_date_out_of_ofsted_date
+    description: >
+      Washwood Heath (139888). Good from a 2020 graded inspection; latest visit
+      an ungraded one in May 2025. ofsted_date is the latest visit.
+    model: dim_school
+    given:
+      - input: ref('stg_gias_establishments')
+        rows:
+          - {urn: 139888, school_name: 'Washwood Heath Academy', status_code: 1, school_type_code: 28, local_authority_code: 330, phase_code: 7}
+      - input: ref('int_ofsted_latest')
+        rows:
+          - {urn: 139888, inspection_date: '2020-03-03', overall_effectiveness: 2, ungraded_grade: null, framework: 'Schools - S5', latest_visit_date: '2025-05-21', current_grade: 2}
+    expect:
+      rows:
+        - {urn: 139888, ofsted_grade: 2, ofsted_date: '2025-05-21'}

pipeline/transform/models/marts/fact_ks4_la_averages.sql

@@ -0,0 +1,22 @@
+{{ config(materialized='table') }}
+
+-- Mart: OFFICIAL DfE KS4 local-authority averages — one row per academic year
+-- and LA (all state-funded schools, all pupils), from the same EES data set
+-- as fact_ks4_national_averages. Feeds "vs LA avg" on search rows and map
+-- cards, replacing a mean the API took over every school in the LA,
+-- independent and special included (audit H2). la_code is the GIAS LA code.
+
+select
+    year,
+    la_code,
+    la_name,
+    attainment_8_score,
+    progress_8_score,
+    english_maths_standard_pass_pct,
+    english_maths_strong_pass_pct,
+    ebacc_entry_pct,
+    ebacc_standard_pass_pct,
+    ebacc_strong_pass_pct,
+    ebacc_avg_score
+from {{ ref('stg_ees_ks4_la') }}
+order by year, la_code

pipeline/transform/models/marts/fact_ofsted_latest.sql

@@ -0,0 +1,37 @@
+-- Mart: current Ofsted status — one row per URN
+-- The backend reads this instead of choosing the latest row of
+-- fact_ofsted_inspection itself. The rule lives in int_ofsted_latest.
+
+select
+    urn,
+    latest_visit_date,
+    latest_visit_kind,
+    latest_visit_outcome,
+    current_grade,
+    current_grade_date,
+    current_grade_basis,
+    graded_inspection_date,
+    ungraded_inspection_date,
+    rc_inspection_date,
+    inspection_type,
+    framework,
+    overall_effectiveness,
+    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
+from {{ ref('int_ofsted_latest') }}

pipeline/transform/models/staging/_stg_sources.yml

@@ -79,6 +79,9 @@ sources:
       - name: ees_ks4_national
         description: Official KS4 national headline averages from DfE EES data catalogue — one row per academic year
 
+      - name: ees_ks4_la
+        description: Official KS4 local-authority averages (all state-funded schools) from the same DfE EES data set as ees_ks4_national — one row per academic year and LA
+
       # Phonics: no school-level data on EES (only national/LA level)
 
       - name: fbit_finance

pipeline/transform/models/staging/stg_ees_ks2.yml

@@ -0,0 +1,22 @@
+version: 2
+
+unit_tests:
+  - name: stg_ees_ks2_reads_percentages_written_with_a_sign
+    description: >
+      DfE's 2023/24 KS2 information file writes percentages as "34%", and every
+      2023/24 percentage loaded as null (audit C2). Plain numbers still load;
+      suppression codes stay null. School 147411's 2023/24 figures are DfE's.
+    model: stg_ees_ks2
+    given:
+      - input: source('raw', 'ees_ks2_attainment')
+        rows:
+          - {school_urn: '147411', time_period: '202324', subject: 'Reading, writing and maths', breakdown_topic: 'All pupils', breakdown: 'Total', expected_standard_pupil_percent: '70'}
+          - {school_urn: '100000', time_period: '202425', subject: 'Reading, writing and maths', breakdown_topic: 'All pupils', breakdown: 'Total', expected_standard_pupil_percent: '79'}
+      - input: source('raw', 'ees_ks2_info')
+        rows:
+          - {school_urn: '147411', time_period: '202324', totpups: '818', telig: '112', ptfsm6cla1a: '34%', ptealgrp2: '56%', psenelk: '20%', psenele: 'c', ptmobn: '87.5%'}
+          - {school_urn: '100000', time_period: '202425', totpups: '792', telig: '105', ptfsm6cla1a: '32', ptealgrp2: 'x', psenelk: '14', psenele: '2', ptmobn: '87'}
+    expect:
+      rows:
+        - {urn: 147411, year: 202324, total_pupils: 818, rwm_expected_pct: 70, disadvantaged_pct: 34, eal_pct: 56, sen_support_pct: 20, sen_ehcp_pct: null, stability_pct: 87.5}
+        - {urn: 100000, year: 202425, total_pupils: 792, rwm_expected_pct: 79, disadvantaged_pct: 32, eal_pct: null, sen_support_pct: 14, sen_ehcp_pct: 2, stability_pct: 87}

pipeline/transform/models/staging/stg_ees_ks4_la.sql

@@ -0,0 +1,21 @@
+-- Staging model: official DfE KS4 local-authority averages — one row per
+-- academic year and LA (all state-funded schools, all pupils). Same EES data
+-- set as stg_ees_ks4_national. la_code is the GIAS LA code
+-- (dim_location.local_authority_code). Suppressed values ('z', 'x') are
+-- coerced to NULL by safe_numeric.
+
+select
+    cast(trim(time_period) as integer)                        as year,
+    cast(trim(old_la_code) as integer)                        as la_code,
+    trim(la_name)                                             as la_name,
+    {{ safe_numeric('attainment_8_score') }}                  as attainment_8_score,
+    {{ safe_numeric('progress_8_score') }}                    as progress_8_score,
+    {{ safe_numeric('english_maths_standard_pass_pct') }}     as english_maths_standard_pass_pct,
+    {{ safe_numeric('english_maths_strong_pass_pct') }}       as english_maths_strong_pass_pct,
+    {{ safe_numeric('ebacc_entry_pct') }}                     as ebacc_entry_pct,
+    {{ safe_numeric('ebacc_standard_pass_pct') }}             as ebacc_standard_pass_pct,
+    {{ safe_numeric('ebacc_strong_pass_pct') }}               as ebacc_strong_pass_pct,
+    {{ safe_numeric('ebacc_avg_score') }}                     as ebacc_avg_score
+from {{ source('raw', 'ees_ks4_la') }}
+where time_period ~ '^[0-9]+$'
+  and old_la_code ~ '^[0-9]+$'

pipeline/transform/models/staging/stg_ees_ks4_la.yml

@@ -0,0 +1,15 @@
+version: 2
+
+unit_tests:
+  - name: stg_ees_ks4_la_casts_codes_years_and_measures
+    description: DfE's LA rows, keyed by the GIAS LA code. Suppressed values ('z') become null.
+    model: stg_ees_ks4_la
+    given:
+      - input: source('raw', 'ees_ks4_la')
+        rows:
+          - {time_period: '202425', old_la_code: '207', new_la_code: 'E09000020', la_name: 'Kensington and Chelsea', attainment_8_score: '54.5', progress_8_score: 'z', english_maths_standard_pass_pct: '77'}
+          - {time_period: '202324', old_la_code: '207', new_la_code: 'E09000020', la_name: 'Kensington and Chelsea', attainment_8_score: '54.5', progress_8_score: '0.29', english_maths_standard_pass_pct: '76'}
+    expect:
+      rows:
+        - {year: 202425, la_code: 207, la_name: 'Kensington and Chelsea', attainment_8_score: 54.5, progress_8_score: null, english_maths_standard_pass_pct: 77}
+        - {year: 202324, la_code: 207, la_name: 'Kensington and Chelsea', attainment_8_score: 54.5, progress_8_score: 0.29, english_maths_standard_pass_pct: 76}

pipeline/transform/models/staging/stg_ofsted_inspections.sql

@@ -1,5 +1,10 @@
 -- Staging model: Ofsted inspection records
--- Handles both OEIF (pre-Nov 2025) and Report Card (post-Nov 2025) frameworks
+-- Handles both OEIF (pre-Nov 2025) and Report Card (post-Nov 2025) frameworks.
+--
+-- Ofsted's MI carries up to three inspections per school: the latest graded
+-- one, the latest ungraded one and the latest report card. Their dates stay
+-- separate here so int_ofsted_latest can tell which came last and which one a
+-- grade belongs to (docs/superpowers/specs/2026-10-05-ofsted-current-status-design.md).
 
 with source as (
     select * from {{ source('raw', 'ofsted_inspections') }}
@@ -8,17 +13,12 @@ with source as (
 renamed as (
     select
         cast(urn as integer)                                                    as urn,
-        -- Inspection event date: the graded inspection when present, otherwise the
-        -- ungraded (Section 8) inspection so schools with only an ungraded
-        -- inspection are still retained.
-        coalesce(
-            to_date(nullif(trim(inspection_date), 'NULL'), 'DD/MM/YYYY'),
-            to_date(nullif(trim(ungraded_inspection_date), 'NULL'), 'DD/MM/YYYY')
-        )                                                                       as inspection_date,
+        to_date(nullif(trim(inspection_date), 'NULL'), 'DD/MM/YYYY')            as graded_inspection_date,
+        to_date(nullif(trim(ungraded_inspection_date), 'NULL'), 'DD/MM/YYYY')   as ungraded_inspection_date,
         inspection_type,
         event_type_grouping                                                     as framework,
 
-        -- OEIF grades (1-4 scale)
+        -- OEIF grades (1-4 scale; 9 = not applicable)
         {{ safe_numeric('overall_effectiveness') }}::integer                    as overall_effectiveness,
         {{ safe_numeric('quality_of_education') }}::integer                     as quality_of_education,
         {{ safe_numeric('behaviour_and_attitudes') }}::integer                  as behaviour_attitudes,
@@ -27,9 +27,9 @@ renamed as (
         {{ safe_numeric('early_years_provision') }}::integer                    as early_years_provision,
         {{ safe_numeric('sixth_form_provision') }}::integer                     as sixth_form_provision,
 
-        -- Ungraded (Section 8) inspection outcome — free text, plus a grade
-        -- parsed from it (1/2/null) used as a last-resort fallback for schools
-        -- with no graded overall effectiveness.
+        -- Ungraded (Section 8) inspection outcome — free text, plus the grade
+        -- it confirms ("School remains Good" → 2); null for outcomes that
+        -- name no grade.
         nullif(trim(ungraded_outcome), 'NULL')                                  as ungraded_outcome,
         {{ parse_ungraded_outcome('ungraded_outcome') }}::integer               as ungraded_grade,
 
@@ -50,31 +50,36 @@ renamed as (
         {{ parse_report_card_grade('rc_sixth_form') }}::integer           as rc_sixth_form,
 
         -- Start date of the latest FULL inspection (the report-card
-        -- inspection in the renewed framework). Guarded in the final select:
-        -- only kept when the row actually carries report-card grades, because
-        -- in legacy-format files this column is the legacy inspection date.
+        -- inspection in the renewed framework). Only kept when the row
+        -- carries report-card grades, because in legacy-format files this
+        -- column is the legacy inspection date.
         to_date(nullif(trim(rc_inspection_date), 'NULL'), 'DD/MM/YYYY')   as rc_inspection_date_raw,
 
         nullif(trim(report_url), 'NULL')                                  as report_url
     from source
     where urn is not null
-      and (
-          nullif(trim(inspection_date), 'NULL') is not null
-          or nullif(trim(ungraded_inspection_date), 'NULL') is not null
-      )
+),
+
+dated as (
+    select
+        *,
+        case
+            when rc_safeguarding_met is not null
+              or rc_inclusion is not null
+              or rc_curriculum_teaching is not null
+              or rc_achievement is not null
+              or rc_attendance_behaviour is not null
+              or rc_personal_development is not null
+              or rc_leadership_governance is not null
+            then rc_inspection_date_raw
+        end as rc_inspection_date
+    from renamed
 )
 
 select
     *,
-    case
-        when rc_safeguarding_met is not null
-          or rc_inclusion is not null
-          or rc_curriculum_teaching is not null
-          or rc_achievement is not null
-          or rc_attendance_behaviour is not null
-          or rc_personal_development is not null
-          or rc_leadership_governance is not null
-        then rc_inspection_date_raw
-    end as rc_inspection_date
-from renamed
-where inspection_date is not null
+    -- For readers that predate the separate dates (fact_ofsted_inspection and
+    -- the backend until it reads fact_ofsted_latest). Never null below.
+    coalesce(graded_inspection_date, ungraded_inspection_date, rc_inspection_date) as inspection_date
+from dated
+where coalesce(graded_inspection_date, ungraded_inspection_date, rc_inspection_date) is not null

pipeline/transform/models/staging/stg_ofsted_inspections.yml

@@ -0,0 +1,25 @@
+version: 2
+
+unit_tests:
+  - name: stg_ofsted_keeps_the_three_dates_apart
+    description: The graded and ungraded dates must stay separate so the latest visit can be found.
+    model: stg_ofsted_inspections
+    given:
+      - input: source('raw', 'ofsted_inspections')
+        rows:
+          - {urn: 102408, inspection_date: '17/06/2025', ungraded_inspection_date: '06/02/2020', overall_effectiveness: 'Not judged', ungraded_outcome: 'School remains Good', rc_inspection_date: '17/06/2025', rc_inclusion: 'NULL'}
+    expect:
+      rows:
+        - {urn: 102408, graded_inspection_date: '2025-06-17', ungraded_inspection_date: '2020-02-06', rc_inspection_date: null, inspection_date: '2025-06-17', ungraded_grade: 2}
+
+  - name: stg_ofsted_keeps_report_card_only_rows
+    description: A school whose only inspection is a report card used to be dropped (audit H3).
+    model: stg_ofsted_inspections
+    given:
+      - input: source('raw', 'ofsted_inspections')
+        rows:
+          - {urn: 149612, inspection_date: 'NULL', ungraded_inspection_date: 'NULL', rc_inspection_date: '10/02/2026', rc_inclusion: 'Expected standard', rc_safeguarding_met: 'Met'}
+          - {urn: 1, inspection_date: 'NULL', ungraded_inspection_date: 'NULL', rc_inspection_date: 'NULL'}
+    expect:
+      rows:
+        - {urn: 149612, graded_inspection_date: null, ungraded_inspection_date: null, rc_inspection_date: '2026-02-10', inspection_date: '2026-02-10', rc_inclusion: 3}

pipeline/transform/tests/assert_ks2_info_percentages_loaded.sql

@@ -0,0 +1,16 @@
+-- Where a year's KS2 school information loaded (pupil counts present), its
+-- percentages loaded too. DfE's files give a disadvantaged % for 96–97% of
+-- those schools; 2023/24 loaded none because the file writes "34%" (audit
+-- C2). A year without an information file (2022/23) has no pupil counts and
+-- is skipped.
+
+select
+    year,
+    count(total_pupils) as with_pupils,
+    count(*) filter (where total_pupils is not null and disadvantaged_pct is not null)
+        as with_disadvantaged
+from {{ ref('stg_ees_ks2') }}
+group by year
+having count(total_pupils) >= 1000
+   and count(*) filter (where total_pupils is not null and disadvantaged_pct is not null)
+       < 0.9 * count(total_pupils)

pipeline/transform/tests/assert_ks4_la_averages_cover_las.sql

@@ -0,0 +1,13 @@
+-- DfE publishes an average for about 152 LAs a year. Fewer than 145 in the
+-- latest year (or none at all) means the LA filter in tap_uk_ees
+-- (ks4_summary.headline_rows) stopped matching, e.g. after DfE renamed a label.
+
+with latest as (
+    select max(year) as year from {{ ref('fact_ks4_la_averages') }}
+)
+
+select l.year, count(f.la_code) as las
+from latest l
+left join {{ ref('fact_ks4_la_averages') }} f on f.year = l.year
+group by l.year
+having count(f.la_code) < 145

pipeline/transform/tests/assert_ks4_la_averages_current.sql

@@ -0,0 +1,20 @@
+{{ config(severity='warn') }}
+
+-- DfE's LA averages cover the latest year with school results. They come from
+-- a fixed EES data set (ks4_summary.KS4_SUMMARY_CSV_URL); when DfE publishes a
+-- new year under a new data set, the school results move on and this mart does
+-- not, so /api/la-averages serves an empty map and every "vs LA avg" goes.
+-- A warning, not an error: it must not hold back a new year's school results.
+
+with schools as (
+    select max(year) as year from {{ ref('stg_ees_ks4') }} where attainment_8_score is not null
+),
+
+las as (
+    select max(year) as year from {{ ref('fact_ks4_la_averages') }}
+)
+
+select s.year as latest_school_year, l.year as latest_la_year
+from schools s
+cross join las l
+where l.year is null or l.year < s.year

pipeline/transform/tests/assert_ks4_years_have_results.sql

@@ -0,0 +1,12 @@
+-- Every year loaded from EES has an Attainment 8 for at least half its
+-- schools. DfE's files reach 82% each year; 2023/24 loaded at 0% after DfE
+-- re-issued its file under older column names (audit C2). Pre-2019 years come
+-- from stg_legacy_ks4 and are not checked here.
+
+select
+    year,
+    count(*) as schools,
+    count(attainment_8_score) as with_attainment_8
+from {{ ref('stg_ees_ks4') }}
+group by year
+having count(attainment_8_score) < 0.5 * count(*)

pipeline/transform/tests/assert_ofsted_current_grade_consistent.sql

@@ -0,0 +1,10 @@
+-- A grade is dated by the inspection that awarded or confirmed it, never
+-- after the latest visit, and has a date and a basis exactly when it exists.
+-- A report card leaves no legacy grade in force.
+
+select urn
+from {{ ref('fact_ofsted_latest') }}
+where current_grade_date > latest_visit_date
+   or (current_grade is null) <> (current_grade_date is null)
+   or (current_grade is null) <> (current_grade_basis is null)
+   or (rc_inspection_date is not null and current_grade is not null)