Merge pull request 'feat: drive sixth-form separation from GIAS OfficialSixthForm flag' (#21) from feat/gias-sixth-form-flag into main

Reviewed-on: #21

backend/app.py

@@ -416,10 +416,17 @@ async def get_schools(
         df_latest = df_latest[df_latest["gender"].str.lower() == gender.lower()]
     if admissions_policy:
         df_latest = df_latest[df_latest["admissions_policy"].str.lower() == admissions_policy.lower()]
-    if has_sixth_form == "yes":
-        df_latest = df_latest[df_latest["age_range"].str.contains("18", na=False)]
-    elif has_sixth_form == "no":
-        df_latest = df_latest[~df_latest["age_range"].str.contains("18", na=False)]
+    # GIAS OfficialSixthForm flag (dim_school.has_sixth_form). NULL (flag not
+    # yet populated by the pipeline) is treated as "no sixth form".
+    if has_sixth_form in ("yes", "no"):
+        if "has_sixth_form" in df_latest.columns:
+            flag = df_latest["has_sixth_form"].eq(True)
+        else:  # Defensive fallback only — data_loader now always synthesizes
+            # has_sixth_form as NULL when the DB predates the pipeline re-run,
+            # so this branch shouldn't normally trigger. Falls back to age
+            # range if the column is somehow absent anyway.
+            flag = df_latest["age_range"].str.contains("18", na=False)
+        df_latest = df_latest[flag if has_sixth_form == "yes" else ~flag]
 
     # Include key result metrics for display on cards
     location_cols = ["latitude", "longitude"]
@@ -596,6 +603,7 @@ async def get_school_details(request: Request, urn: int):
             "address": latest.get("address", ""),
             "religious_denomination": latest.get("religious_denomination", ""),
             "age_range": latest.get("age_range", ""),
+            "has_sixth_form": latest.get("has_sixth_form"),
             "latitude": latest.get("latitude"),
             "longitude": latest.get("longitude"),
             "phase": latest.get("phase"),

backend/data_loader.py

@@ -3,11 +3,14 @@ Data loading module — reads from marts.* tables built by dbt.
 Provides efficient queries with caching.
 """
 
+import logging
+
 import pandas as pd
 import numpy as np
 from typing import Optional, Dict, Tuple, List
 import requests
 from sqlalchemy import text
+import sqlalchemy.exc
 from sqlalchemy.orm import Session
 
 from .config import settings
@@ -125,6 +128,7 @@ _MAIN_QUERY = text("""
         s.religious_character  AS religious_denomination,
         s.gender,
         s.age_range,
+        s.has_sixth_form,
         s.admissions_policy,
         s.capacity,
         s.total_pupils         AS gias_total_pupils,
@@ -214,11 +218,36 @@ _MAIN_QUERY = text("""
     ORDER BY s.school_name, p.year
 """)
 
+# Fallback used when marts.dim_school predates the has_sixth_form column
+# (i.e. the nightly dbt pipeline hasn't rebuilt the mart yet on this DB).
+# Keeps the column present as NULL so downstream code — including the
+# app.py fallback branch — behaves as designed instead of KeyError-ing.
+_MAIN_QUERY_NO_SIXTH_FORM = text(
+    str(_MAIN_QUERY).replace("s.has_sixth_form,", "NULL AS has_sixth_form,")
+)
+assert "NULL AS has_sixth_form" in str(_MAIN_QUERY_NO_SIXTH_FORM), (
+    "expected replacement of 's.has_sixth_form,' to have taken effect"
+)
+
 
 def load_school_data_as_dataframe() -> pd.DataFrame:
     """Load all school + KS2 data as a pandas DataFrame."""
     try:
         df = pd.read_sql(_MAIN_QUERY, engine)
+    except sqlalchemy.exc.ProgrammingError as exc:
+        if "has_sixth_form" not in str(exc):
+            print(f"Warning: Could not load school data from marts: {exc}")
+            return pd.DataFrame()
+        logging.getLogger(__name__).warning(
+            "marts.dim_school is missing has_sixth_form (pipeline hasn't "
+            "rebuilt the mart yet on this DB) — retrying without it: %s",
+            exc,
+        )
+        try:
+            df = pd.read_sql(_MAIN_QUERY_NO_SIXTH_FORM, engine)
+        except Exception as exc2:
+            print(f"Warning: Could not load school data from marts: {exc2}")
+            return pd.DataFrame()
     except Exception as exc:
         print(f"Warning: Could not load school data from marts: {exc}")
         return pd.DataFrame()

backend/models.py

@@ -24,6 +24,7 @@ class DimSchool(Base):
     religious_character = Column(String(100))
     gender = Column(String(20))
     age_range = Column(String(20))
+    has_sixth_form = Column(Boolean)
     capacity = Column(Integer)
     total_pupils = Column(Integer)
     headteacher_name = Column(String(200))

backend/schemas.py

@@ -543,6 +543,7 @@ SCHOOL_COLUMNS = [
     "postcode",
     "religious_denomination",
     "age_range",
+    "has_sixth_form",
     "gender",
     "admissions_policy",
     "ofsted_grade",

backend/tests/test_sixth_form_flag.py

@@ -0,0 +1,173 @@
+"""Tests for the GIAS-driven has_sixth_form flag (spec 2026-07-07 §3).
+
+The filter and payloads must use dim_school.has_sixth_form, not the old
+age_range-contains-"18" substring heuristic. The key regression case is a
+16-19 sixth-form college: flag true, but "16-19" contains no "18".
+"""
+
+import numpy as np
+import pandas as pd
+import pytest
+from fastapi.testclient import TestClient
+
+
+def _schools_df() -> pd.DataFrame:
+    """Latest-year snapshot rows as produced by load_latest_school_data."""
+    base = {
+        "local_authority": "Testshire",
+        "school_type": "Academy",
+        "phase": "Secondary",
+        "address": "1 Test Street",
+        "town": "Testtown",
+        "postcode": "TS1 1AA",
+        "religious_denomination": None,
+        "gender": "Mixed",
+        "admissions_policy": None,
+        "ofsted_grade": np.nan,
+        "ofsted_date": None,
+        "ofsted_framework": None,
+        "latitude": 51.5,
+        "longitude": -0.1,
+        "year": 202425,
+        "total_pupils": 1000,
+        "rwm_expected_pct": np.nan,
+        "attainment_8_score": 50.0,
+    }
+    return pd.DataFrame(
+        [
+            # 11-18 school WITH a registered sixth form
+            {**base, "urn": 100001, "school_name": "Alpha High",
+             "age_range": "11-18", "has_sixth_form": True},
+            # 16-19 college: old heuristic said NO ("16-19" has no "18"),
+            # GIAS flag says YES — must appear in the yes-filter results
+            {**base, "urn": 100002, "school_name": "Beta Sixth Form College",
+             "age_range": "16-19", "has_sixth_form": True},
+            # 11-18 age range on paper but NO registered sixth form:
+            # old heuristic said YES, GIAS flag says NO
+            {**base, "urn": 100003, "school_name": "Gamma Academy",
+             "age_range": "11-18", "has_sixth_form": False},
+            # Missing flag (pipeline not yet re-run) — must not crash,
+            # must not match the yes-filter
+            {**base, "urn": 100004, "school_name": "Delta School",
+             "age_range": "11-16", "has_sixth_form": None},
+        ]
+    )
+
+
+@pytest.fixture()
+def client(monkeypatch):
+    from backend import app as app_module
+
+    monkeypatch.setattr(app_module, "load_latest_school_data", _schools_df)
+    monkeypatch.setattr(app_module, "load_school_data", _schools_df)
+    monkeypatch.setattr(app_module, "get_supplementary_data", lambda db, urn: {})
+    return TestClient(app_module.app, raise_server_exceptions=False)
+
+
+def _urns(resp):
+    return sorted(s["urn"] for s in resp.json()["schools"])
+
+
+def test_filter_yes_uses_flag_not_age_range(client):
+    resp = client.get("/api/schools?has_sixth_form=yes")
+    assert resp.status_code == 200, resp.text
+    # 16-19 college included; 11-18-without-sixth-form excluded
+    assert _urns(resp) == [100001, 100002]
+
+
+def test_filter_no_uses_flag_not_age_range(client):
+    resp = client.get("/api/schools?has_sixth_form=no")
+    assert resp.status_code == 200, resp.text
+    # Gamma (flag false) and Delta (flag missing => not true)
+    assert _urns(resp) == [100003, 100004]
+
+
+def test_list_payload_includes_flag(client):
+    resp = client.get("/api/schools")
+    assert resp.status_code == 200, resp.text
+    by_urn = {s["urn"]: s for s in resp.json()["schools"]}
+    assert by_urn[100002]["has_sixth_form"] is True
+    assert by_urn[100003]["has_sixth_form"] is False
+    assert by_urn[100004]["has_sixth_form"] is None
+
+
+def test_detail_payload_includes_flag(client):
+    resp = client.get("/api/schools/100002")
+    assert resp.status_code == 200, resp.text
+    assert resp.json()["school_info"]["has_sixth_form"] is True
+
+
+def test_detail_payload_serializes_numpy_bool(monkeypatch):
+    """Once the pipeline has run, has_sixth_form is a real bool dtype column
+    (dbt not_null test guarantees no NULLs), so row access yields
+    numpy.bool_ rather than a Python bool. convert_to_native must handle it —
+    otherwise FastAPI's jsonable_encoder raises ValueError and the detail
+    endpoint 500s (C2)."""
+    from backend import app as app_module
+
+    df = _schools_df()
+    # Drop the row with a None flag — this fixture models the post-pipeline
+    # state where the column is a genuine, fully-populated bool dtype.
+    df = df[df["has_sixth_form"].notna()].reset_index(drop=True)
+    df["has_sixth_form"] = df["has_sixth_form"].astype(bool)
+    assert df["has_sixth_form"].dtype == bool
+
+    monkeypatch.setattr(app_module, "load_school_data", lambda: df)
+    monkeypatch.setattr(app_module, "get_supplementary_data", lambda db, urn: {})
+    client = TestClient(app_module.app, raise_server_exceptions=False)
+
+    resp = client.get("/api/schools/100002")
+    assert resp.status_code == 200, resp.text
+    assert resp.json()["school_info"]["has_sixth_form"] is True
+
+
+def test_load_school_data_survives_missing_has_sixth_form_column(monkeypatch):
+    """Real prod state until the nightly pipeline first rebuilds the mart:
+    marts.dim_school lacks has_sixth_form entirely. The first query raises
+    UndefinedColumn; load_school_data_as_dataframe must retry without the
+    column (synthesizing it as None) rather than swallow the error and
+    return (and then have load_school_data cache) an empty DataFrame (C1)."""
+    import sqlalchemy.exc
+    from backend import data_loader
+
+    data_loader._df_cache = None
+    data_loader._df_latest_cache = None
+
+    good_df = pd.DataFrame(
+        [
+            {
+                "urn": 1,
+                "school_name": "Fallback School",
+                "school_type": "Academy",
+                "has_sixth_form": None,
+            }
+        ]
+    )
+    calls = []
+
+    def fake_read_sql(query, con):
+        calls.append(query)
+        if len(calls) == 1:
+            raise sqlalchemy.exc.ProgrammingError(
+                "SELECT ...",
+                None,
+                Exception(
+                    "(psycopg2.errors.UndefinedColumn) column s.has_sixth_form "
+                    "does not exist"
+                ),
+            )
+        return good_df.copy()
+
+    monkeypatch.setattr(data_loader.pd, "read_sql", fake_read_sql)
+
+    try:
+        df = data_loader.load_school_data_as_dataframe()
+    finally:
+        data_loader._df_cache = None
+        data_loader._df_latest_cache = None
+
+    assert len(calls) == 2, "must retry with the no-sixth-form query variant"
+    assert calls[1] is data_loader._MAIN_QUERY_NO_SIXTH_FORM
+    assert not df.empty
+    assert "has_sixth_form" in df.columns
+    assert df["has_sixth_form"].iloc[0] is None

backend/utils.py

@@ -11,6 +11,8 @@ def convert_to_native(value: Any) -> Any:
     """Convert numpy types to native Python types for JSON serialization."""
     if pd.isna(value):
         return None
+    if isinstance(value, np.bool_):
+        return bool(value)
     if isinstance(value, (np.integer,)):
         return int(value)
     if isinstance(value, (np.floating,)):

docs/superpowers/plans/2026-07-07-gias-sixth-form-flag.md

@@ -0,0 +1,560 @@
+# GIAS OfficialSixthForm Flag Implementation Plan
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** Ingest GIAS's authoritative `OfficialSixthForm` flag into `marts.dim_school.has_sixth_form` and replace every `age_range contains "18"` heuristic in the backend and frontend with it.
+
+**Architecture:** Data flows tap → raw → dbt staging → dbt mart → backend SQL → API payload → Next.js components. The GIAS Singer tap must declare the new CSV column (target-postgres only persists declared columns); the dbt staging model renames it; `dim_school` derives a boolean (with a statutory-age fallback for blank GIAS values); the backend exposes it on list + detail payloads and uses it for the `has_sixth_form=yes|no` filter; the frontend badge/note/filter-labels switch from the age-range substring check to the flag.
+
+**Tech Stack:** Singer SDK (tap), dbt (Postgres), FastAPI + pandas, Next.js + TypeScript, pytest, Jest/RTL.
+
+**Spec:** `docs/superpowers/specs/2026-07-07-exam-phase-taxonomy-design.md` §3.
+
+## Global Constraints
+
+- A school **has a sixth form** iff GIAS `OfficialSixthForm (name)` = `"Has a sixth form"`. `"Does not have a sixth form"` and `"Not applicable"` → false. Blank/NULL (rare) → fall back to `statutory_high_age >= 18`.
+- The public API filter parameter stays `has_sixth_form=yes|no` (unchanged contract).
+- Filter dropdown labels must drop the age-range parentheticals: "With sixth form" / "Without sixth form" (sixth form ≠ age range).
+- Never push to `main`; work stays on branch `feat/gias-sixth-form-flag` (create from `docs/exam-phase-taxonomy` so the spec is included, or from `main` if that branch has merged).
+- The dbt models cannot be run locally (no pipeline DB); dbt changes are verified by review + `python -c` schema asserts + existing CI. Do NOT attempt to start a local server.
+- The backend marts tables are dbt `table` materializations — rebuilt on every pipeline run, so **no ALTER TABLE migration is needed** for `marts.dim_school`.
+- Deployment ordering: the tap must run before dbt on the first pipeline run after deploy (this is already the DAG order: extract → transform). Until that run happens, `has_sixth_form` is absent from the DB; the backend must treat a missing column as "flag false / fallback", never crash.
+
+---
+
+### Task 1: Ingest `OfficialSixthForm (name)` — tap schema + dbt staging
+
+**Files:**
+- Modify: `pipeline/plugins/extractors/tap-uk-gias/tap_uk_gias/tap.py:31-66` (Singer schema)
+- Modify: `pipeline/transform/models/staging/stg_gias_establishments.sql` (add renamed column)
+
+**Interfaces:**
+- Produces: raw column `"OfficialSixthForm (name)"` in `raw.gias_establishments`; staging column `official_sixth_form` (text: `Has a sixth form` / `Does not have a sixth form` / `Not applicable` / NULL) consumed by Task 2.
+
+- [ ] **Step 1: Add the property to the Singer schema**
+
+In `tap.py`, inside `GIASEstablishmentsStream.schema = th.PropertiesList(...)`, add after the `th.Property("PhaseOfEducation (name)", th.StringType),` line:
+
+```python
+        th.Property("OfficialSixthForm (name)", th.StringType),
+```
+
+- [ ] **Step 2: Verify the tap module still imports and declares the column**
+
+Run:
+```bash
+cd /Users/tudor/projects/school_compare/pipeline/plugins/extractors/tap-uk-gias && \
+python3 -c "
+import ast, sys
+src = open('tap_uk_gias/tap.py').read()
+ast.parse(src)
+assert '\"OfficialSixthForm (name)\"' in src.replace(\"'\", '\"')
+print('OK: tap declares OfficialSixthForm (name)')
+"
+```
+Expected: `OK: tap declares OfficialSixthForm (name)`
+(Uses `ast.parse` instead of importing because `singer_sdk` is not installed locally.)
+
+- [ ] **Step 3: Add the column to the staging model**
+
+In `stg_gias_establishments.sql`, in the `renamed` CTE, add after the `"PhaseOfEducation (name)" as phase,` line:
+
+```sql
+        nullif(trim("OfficialSixthForm (name)"), '')    as official_sixth_form,
+```
+
+- [ ] **Step 4: Sanity-check the SQL edit**
+
+Run:
+```bash
+grep -n "official_sixth_form" /Users/tudor/projects/school_compare/pipeline/transform/models/staging/stg_gias_establishments.sql
+```
+Expected: one line showing the new column inside the `renamed` CTE (before `from source`).
+
+- [ ] **Step 5: Commit**
+
+```bash
+git add pipeline/plugins/extractors/tap-uk-gias/tap_uk_gias/tap.py pipeline/transform/models/staging/stg_gias_establishments.sql
+git commit -m "feat(pipeline): ingest GIAS OfficialSixthForm into staging
+
+Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>"
+```
+
+---
+
+### Task 2: Derive `dim_school.has_sixth_form` (dbt mart + schema tests + SQLAlchemy model)
+
+**Files:**
+- Modify: `pipeline/transform/models/marts/dim_school.sql` (add derived column)
+- Modify: `pipeline/transform/models/marts/_marts_schema.yml` (document + test the column)
+- Modify: `backend/models.py:13-38` (`DimSchool` — add column)
+
+**Interfaces:**
+- Consumes: `official_sixth_form` text column from Task 1's staging model.
+- Produces: `marts.dim_school.has_sixth_form boolean not null`, and `DimSchool.has_sixth_form = Column(Boolean)` for the backend. Task 3 selects it as `s.has_sixth_form`.
+
+- [ ] **Step 1: Add the derived column to `dim_school.sql`**
+
+In the `select`, add after the `s.age_range` line (`s.statutory_low_age || '-' || s.statutory_high_age as age_range,`):
+
+```sql
+    -- Authoritative sixth-form flag (spec §3): GIAS OfficialSixthForm.
+    -- "Not applicable" (nurseries, primaries, PRUs) => false. Blank GIAS
+    -- value (rare, new establishments) falls back to the statutory age range.
+    case
+        when s.official_sixth_form = 'Has a sixth form' then true
+        when s.official_sixth_form in ('Does not have a sixth form', 'Not applicable') then false
+        else coalesce(s.statutory_high_age >= 18, false)
+    end as has_sixth_form,
+```
+
+- [ ] **Step 2: Add schema documentation + tests in `_marts_schema.yml`**
+
+Under `- name: dim_school` → `columns:`, add after the `phase` column block:
+
+```yaml
+      - name: has_sixth_form
+        description: >
+          Authoritative sixth-form flag from GIAS OfficialSixthForm.
+          "Has a sixth form" => true; "Does not have a sixth form" and
+          "Not applicable" => false; blank GIAS value falls back to
+          statutory_high_age >= 18. Replaces the age_range-contains-"18"
+          heuristic (spec 2026-07-07 §3).
+        tests:
+          - not_null
+          - accepted_values:
+              values: [true, false]
+```
+
+- [ ] **Step 3: Add the column to the `DimSchool` SQLAlchemy model**
+
+In `backend/models.py`, in `class DimSchool`, add after `age_range = Column(String(20))`:
+
+```python
+    has_sixth_form = Column(Boolean)
+```
+
+- [ ] **Step 4: Verify SQL/YAML/Python all parse**
+
+Run:
+```bash
+cd /Users/tudor/projects/school_compare && \
+python3 -c "
+import yaml
+y = yaml.safe_load(open('pipeline/transform/models/marts/_marts_schema.yml'))
+dim = [m for m in y['models'] if m['name'] == 'dim_school'][0]
+cols = [c['name'] for c in dim['columns']]
+assert 'has_sixth_form' in cols, cols
+print('OK: schema yml documents has_sixth_form')
+" && \
+grep -c "has_sixth_form" pipeline/transform/models/marts/dim_school.sql && \
+python3 -c "import ast; ast.parse(open('backend/models.py').read()); print('OK: models.py parses')"
+```
+Expected: `OK: schema yml documents has_sixth_form`, grep count `>= 1`, `OK: models.py parses`.
+
+- [ ] **Step 5: Commit**
+
+```bash
+git add pipeline/transform/models/marts/dim_school.sql pipeline/transform/models/marts/_marts_schema.yml backend/models.py
+git commit -m "feat(pipeline): derive dim_school.has_sixth_form from GIAS flag
+
+Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>"
+```
+
+---
+
+### Task 3: Backend — expose `has_sixth_form` and replace the filter heuristic
+
+**Files:**
+- Modify: `backend/data_loader.py:117-215` (`_MAIN_QUERY` — select the column)
+- Modify: `backend/schemas.py:536-553` (`SCHOOL_COLUMNS` — include in list payloads)
+- Modify: `backend/app.py:419-422` (filter) and `backend/app.py:589-610` (detail `school_info`)
+- Test: `backend/tests/test_sixth_form_flag.py` (new)
+
+**Interfaces:**
+- Consumes: `marts.dim_school.has_sixth_form` (Task 2).
+- Produces: `has_sixth_form: bool | null` field on `GET /api/schools` items and on `GET /api/schools/{urn}` → `school_info`. Filter `GET /api/schools?has_sixth_form=yes|no` now driven by the flag. Frontend (Task 4) reads `school.has_sixth_form`.
+
+- [ ] **Step 1: Write the failing tests**
+
+Create `backend/tests/test_sixth_form_flag.py`:
+
+```python
+"""Tests for the GIAS-driven has_sixth_form flag (spec 2026-07-07 §3).
+
+The filter and payloads must use dim_school.has_sixth_form, not the old
+age_range-contains-"18" substring heuristic. The key regression case is a
+16-19 sixth-form college: flag true, but "16-19" contains no "18".
+"""
+
+import numpy as np
+import pandas as pd
+import pytest
+from fastapi.testclient import TestClient
+
+
+def _schools_df() -> pd.DataFrame:
+    """Latest-year snapshot rows as produced by load_latest_school_data."""
+    base = {
+        "local_authority": "Testshire",
+        "school_type": "Academy",
+        "phase": "Secondary",
+        "address": "1 Test Street",
+        "town": "Testtown",
+        "postcode": "TS1 1AA",
+        "religious_denomination": None,
+        "gender": "Mixed",
+        "admissions_policy": None,
+        "ofsted_grade": np.nan,
+        "ofsted_date": None,
+        "ofsted_framework": None,
+        "latitude": 51.5,
+        "longitude": -0.1,
+        "year": 202425,
+        "total_pupils": 1000,
+        "rwm_expected_pct": np.nan,
+        "attainment_8_score": 50.0,
+    }
+    return pd.DataFrame(
+        [
+            # 11-18 school WITH a registered sixth form
+            {**base, "urn": 100001, "school_name": "Alpha High",
+             "age_range": "11-18", "has_sixth_form": True},
+            # 16-19 college: old heuristic said NO ("16-19" has no "18"),
+            # GIAS flag says YES — must appear in the yes-filter results
+            {**base, "urn": 100002, "school_name": "Beta Sixth Form College",
+             "age_range": "16-19", "has_sixth_form": True},
+            # 11-18 age range on paper but NO registered sixth form:
+            # old heuristic said YES, GIAS flag says NO
+            {**base, "urn": 100003, "school_name": "Gamma Academy",
+             "age_range": "11-18", "has_sixth_form": False},
+            # Missing flag (pipeline not yet re-run) — must not crash,
+            # must not match the yes-filter
+            {**base, "urn": 100004, "school_name": "Delta School",
+             "age_range": "11-16", "has_sixth_form": None},
+        ]
+    )
+
+
+@pytest.fixture()
+def client(monkeypatch):
+    from backend import app as app_module
+
+    monkeypatch.setattr(app_module, "load_latest_school_data", _schools_df)
+    monkeypatch.setattr(app_module, "load_school_data", _schools_df)
+    monkeypatch.setattr(app_module, "get_supplementary_data", lambda db, urn: {})
+    return TestClient(app_module.app, raise_server_exceptions=False)
+
+
+def _urns(resp):
+    return sorted(s["urn"] for s in resp.json()["schools"])
+
+
+def test_filter_yes_uses_flag_not_age_range(client):
+    resp = client.get("/api/schools?has_sixth_form=yes")
+    assert resp.status_code == 200, resp.text
+    # 16-19 college included; 11-18-without-sixth-form excluded
+    assert _urns(resp) == [100001, 100002]
+
+
+def test_filter_no_uses_flag_not_age_range(client):
+    resp = client.get("/api/schools?has_sixth_form=no")
+    assert resp.status_code == 200, resp.text
+    # Gamma (flag false) and Delta (flag missing => not true)
+    assert _urns(resp) == [100003, 100004]
+
+
+def test_list_payload_includes_flag(client):
+    resp = client.get("/api/schools")
+    assert resp.status_code == 200, resp.text
+    by_urn = {s["urn"]: s for s in resp.json()["schools"]}
+    assert by_urn[100002]["has_sixth_form"] is True
+    assert by_urn[100003]["has_sixth_form"] is False
+    assert by_urn[100004]["has_sixth_form"] is None
+
+
+def test_detail_payload_includes_flag(client):
+    resp = client.get("/api/schools/100002")
+    assert resp.status_code == 200, resp.text
+    assert resp.json()["school_info"]["has_sixth_form"] is True
+```
+
+- [ ] **Step 2: Run tests to verify they fail**
+
+Run: `cd /Users/tudor/projects/school_compare && python3 -m pytest backend/tests/test_sixth_form_flag.py -v`
+Expected: FAIL — `test_filter_yes_uses_flag_not_age_range` asserts `[100001, 100002]` but the age-range heuristic returns `[100001, 100003]`; the payload tests fail with `KeyError: 'has_sixth_form'`.
+
+- [ ] **Step 3: Select the column in `_MAIN_QUERY`**
+
+In `backend/data_loader.py`, in `_MAIN_QUERY`, add after `s.age_range,`:
+
+```sql
+        s.has_sixth_form,
+```
+
+- [ ] **Step 4: Include it in list payloads**
+
+In `backend/schemas.py`, in `SCHOOL_COLUMNS`, add after `"age_range",`:
+
+```python
+    "has_sixth_form",
+```
+
+(`app.py` builds list responses from `SCHOOL_COLUMNS ∩ df.columns`, so a DB that predates the pipeline re-run simply omits the field — no crash.)
+
+- [ ] **Step 5: Replace the filter heuristic in `app.py`**
+
+Replace lines 419-422:
+
+```python
+    if has_sixth_form == "yes":
+        df_latest = df_latest[df_latest["age_range"].str.contains("18", na=False)]
+    elif has_sixth_form == "no":
+        df_latest = df_latest[~df_latest["age_range"].str.contains("18", na=False)]
+```
+
+with:
+
+```python
+    # GIAS OfficialSixthForm flag (dim_school.has_sixth_form). NULL (flag not
+    # yet populated by the pipeline) is treated as "no sixth form".
+    if has_sixth_form in ("yes", "no"):
+        if "has_sixth_form" in df_latest.columns:
+            flag = df_latest["has_sixth_form"].eq(True)
+        else:  # DB predates the pipeline re-run — fall back to age range
+            flag = df_latest["age_range"].str.contains("18", na=False)
+        df_latest = df_latest[flag if has_sixth_form == "yes" else ~flag]
+```
+
+- [ ] **Step 6: Add the flag to the detail payload**
+
+In `backend/app.py` `school_info` dict (line ~598), add after `"age_range": latest.get("age_range", ""),`:
+
+```python
+            "has_sixth_form": latest.get("has_sixth_form"),
+```
+
+(`convert_to_native` already maps NaN/None → null and numpy bools → bool.)
+
+- [ ] **Step 7: Run the new tests**
+
+Run: `cd /Users/tudor/projects/school_compare && python3 -m pytest backend/tests/test_sixth_form_flag.py -v`
+Expected: 4 passed.
+
+- [ ] **Step 8: Run the full backend suite**
+
+Run: `cd /Users/tudor/projects/school_compare && python3 -m pytest backend/tests -v`
+Expected: all pass (the pre-existing `test_school_details.py` df has no `has_sixth_form` column — `latest.get()` returns None, serialized as null).
+
+- [ ] **Step 9: Commit**
+
+```bash
+git add backend/data_loader.py backend/schemas.py backend/app.py backend/tests/test_sixth_form_flag.py
+git commit -m "feat(api): drive has_sixth_form filter and payloads from GIAS flag
+
+Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>"
+```
+
+---
+
+### Task 4: Frontend — badge, note, row tag, and filter labels use the flag
+
+**Files:**
+- Modify: `nextjs-app/lib/types.ts:10-30` (`School` interface)
+- Modify: `nextjs-app/components/SecondarySchoolDetailView.tsx:101` (badge + coming-soon note)
+- Modify: `nextjs-app/components/SecondarySchoolRow.tsx:25-27` (row tag)
+- Modify: `nextjs-app/components/FilterBar.tsx:370-372` (labels only — param name unchanged)
+- Test: `nextjs-app/__tests__/components/SecondarySchoolRow.test.tsx` (new)
+
+**Interfaces:**
+- Consumes: `has_sixth_form: boolean | null` on both list items and `school_info` (Task 3; both are typed as `School`).
+- Produces: no new exports — behavior change only.
+
+- [ ] **Step 1: Write the failing test**
+
+Create `nextjs-app/__tests__/components/SecondarySchoolRow.test.tsx`:
+
+```tsx
+/**
+ * SecondarySchoolRow — sixth-form tag must come from the GIAS
+ * has_sixth_form flag, not the age_range-contains-"18" heuristic.
+ */
+
+import '@testing-library/jest-dom';
+import { render, screen } from '@testing-library/react';
+import { SecondarySchoolRow } from '@/components/SecondarySchoolRow';
+import type { School } from '@/lib/types';
+
+const base = {
+  urn: 100002,
+  school_name: 'Beta Sixth Form College',
+  local_authority: 'Testshire',
+  school_type: 'Academy',
+  phase: 'Secondary',
+  gender: 'Mixed',
+  attainment_8_score: 50.0,
+} as unknown as School;
+
+describe('SecondarySchoolRow sixth-form tag', () => {
+  it('shows the tag for a 16-19 college with the GIAS flag set', () => {
+    render(
+      <SecondarySchoolRow
+        school={{ ...base, age_range: '16-19', has_sixth_form: true }}
+      />,
+    );
+    expect(screen.getByText('Sixth form')).toBeInTheDocument();
+  });
+
+  it('hides the tag for an 11-18 school without a registered sixth form', () => {
+    render(
+      <SecondarySchoolRow
+        school={{ ...base, age_range: '11-18', has_sixth_form: false }}
+      />,
+    );
+    expect(screen.queryByText('Sixth form')).not.toBeInTheDocument();
+  });
+
+  it('hides the tag when the flag is missing (pipeline not yet re-run)', () => {
+    render(
+      <SecondarySchoolRow school={{ ...base, age_range: '11-18' }} />,
+    );
+    expect(screen.queryByText('Sixth form')).not.toBeInTheDocument();
+  });
+});
+```
+
+- [ ] **Step 2: Run it to verify it fails**
+
+Run: `cd /Users/tudor/projects/school_compare/nextjs-app && npx jest __tests__/components/SecondarySchoolRow.test.tsx`
+Expected: FAIL — first test can't find "Sixth form" ("16-19" fails the substring check), second test finds an unexpected "Sixth form" tag. (If TS complains that `has_sixth_form` is not on `School`, that is the same failure — proceed.)
+
+- [ ] **Step 3: Add the field to the `School` type**
+
+In `nextjs-app/lib/types.ts`, in `export interface School`, add after `age_range: string | null;`:
+
+```ts
+  has_sixth_form?: boolean | null;
+```
+
+- [ ] **Step 4: Switch `SecondarySchoolRow` to the flag**
+
+Replace the helper at `SecondarySchoolRow.tsx:25-27`:
+
+```ts
+function hasSixthForm(school: School): boolean {
+  return school.age_range?.includes('18') ?? false;
+}
+```
+
+with:
+
+```ts
+function hasSixthForm(school: School): boolean {
+  // GIAS OfficialSixthForm flag; missing (pipeline not yet re-run) => false.
+  return school.has_sixth_form ?? false;
+}
+```
+
+- [ ] **Step 5: Switch `SecondarySchoolDetailView` to the flag**
+
+Replace line 101:
+
+```ts
+  const hasSixthForm = schoolInfo.age_range?.includes('18') ?? false;
+```
+
+with:
+
+```ts
+  // GIAS OfficialSixthForm flag; missing (pipeline not yet re-run) => false.
+  const hasSixthForm = schoolInfo.has_sixth_form ?? false;
+```
+
+(This drives both the header "Sixth form" badge at line ~230 and the "Post-16 destination data coming soon" note at line ~715 — no changes needed there.)
+
+- [ ] **Step 6: Fix the filter labels in `FilterBar.tsx`**
+
+Replace:
+
+```tsx
+                    <option value="yes">With sixth form (11-18)</option>
+                    <option value="no">Without sixth form (11-16)</option>
+```
+
+with:
+
+```tsx
+                    <option value="yes">With sixth form</option>
+                    <option value="no">Without sixth form</option>
+```
+
+- [ ] **Step 7: Run the new test and verify it passes**
+
+Run: `cd /Users/tudor/projects/school_compare/nextjs-app && npx jest __tests__/components/SecondarySchoolRow.test.tsx`
+Expected: 3 passed.
+
+- [ ] **Step 8: Run the full frontend checks**
+
+Run: `cd /Users/tudor/projects/school_compare/nextjs-app && npx tsc --noEmit && npx jest`
+Expected: typecheck clean, all Jest suites pass.
+
+- [ ] **Step 9: Verify no heuristic remains**
+
+Run:
+```bash
+grep -rn "includes('18')\|contains(\"18\")" /Users/tudor/projects/school_compare/nextjs-app/components /Users/tudor/projects/school_compare/backend --include="*.tsx" --include="*.ts" --include="*.py" | grep -v test
+```
+Expected: only the documented fallback inside `app.py` (DB-predates-pipeline branch); no other hits.
+
+- [ ] **Step 10: Commit**
+
+```bash
+git add nextjs-app/lib/types.ts nextjs-app/components/SecondarySchoolRow.tsx nextjs-app/components/SecondarySchoolDetailView.tsx nextjs-app/components/FilterBar.tsx nextjs-app/__tests__/components/SecondarySchoolRow.test.tsx
+git commit -m "feat(ui): sixth-form badge, note and filter labels use GIAS flag
+
+Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>"
+```
+
+---
+
+### Task 5: Update the spec status + PR
+
+**Files:**
+- Modify: `docs/superpowers/specs/2026-07-07-exam-phase-taxonomy-design.md` (§3 "Pipeline change (future work)" → implemented)
+
+**Interfaces:**
+- Consumes: everything above merged into the branch.
+- Produces: PR ready for review; e2e journeys are the promotion gate (no journey currently exercises the sixth-form filter, and the API contract is unchanged, so no e2e change is required — state this in the PR body).
+
+- [ ] **Step 1: Mark spec §3 pipeline change as implemented**
+
+In the spec, change the §3 heading `### Pipeline change (future work)` to `### Pipeline change (implemented 2026-07-07)` and append one line at the end of that subsection:
+
+```markdown
+Implemented in `feat/gias-sixth-form-flag` — see
+`docs/superpowers/plans/2026-07-07-gias-sixth-form-flag.md`.
+```
+
+- [ ] **Step 2: Commit**
+
+```bash
+git add docs/superpowers/specs/2026-07-07-exam-phase-taxonomy-design.md
+git commit -m "docs: mark sixth-form flag pipeline change implemented
+
+Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>"
+```
+
+- [ ] **Step 3: Push and open the PR (Gitea)**
+
+Push the branch, then create the PR against `main` using the Gitea API via the git credential helper (token-header auth 401s on this Gitea; basic auth from `git credential fill` works):
+
+```bash
+git push -u origin feat/gias-sixth-form-flag
+```
+
+PR title: `feat: drive sixth-form separation from GIAS OfficialSixthForm flag`
+PR body must note: (1) API contract unchanged (`has_sixth_form=yes|no`), (2) flag is NULL until the next pipeline run — backend and frontend degrade to "no sixth form" / age-range fallback, (3) no e2e journey change needed, and end with the standard generation footer.
+
+- [ ] **Step 4: Verify CI passes**
+
+Watch the PR checks (typecheck, tests, builds, AI review). All must pass before merge; merging deploys to staging automatically.

docs/superpowers/specs/2026-07-07-exam-phase-taxonomy-design.md

@@ -0,0 +1,215 @@
+# Exam Results Taxonomy — Phase Grouping and Sixth-Form Separation
+
+**Date:** 2026-07-07
+**Status:** Approved design (taxonomy/analysis only — no implementation in this doc's scope)
+
+## Purpose
+
+Classify every exam-result metric SchoolCompare displays today into four phase
+groups — **Primary**, **Secondary**, **Sixth form**, **Other** — and define an
+authoritative rule for separating schools that have a sixth form from those
+that don't. This document is the reference for:
+
+1. How the UI should group results sections and rankings by phase.
+2. The future KS5 (A-level) ingestion work — the Sixth form group lists the
+   concrete DfE metrics as placeholders with source columns.
+3. Replacing the fragile `age_range contains "18"` heuristic with the GIAS
+   `OfficialSixthForm` flag.
+
+## 1. Grouping principle
+
+Metrics are grouped by **the key stage of the assessment**, not by the phase
+of the school displaying them. An all-through school (4–18) shows metrics in
+all three exam groups; a pure primary shows only the Primary group.
+
+| Group | Assessments | Key stage | Taken at age | Data status |
+|---|---|---|---|---|
+| **Primary** | KS2 SATs (reading, writing TA, maths, GPS, science TA) | KS2 | 10–11 (Year 6) | ✅ Live — `marts.fact_ks2_performance` |
+| **Secondary** | GCSEs, Attainment 8 / Progress 8, EBacc | KS4 | 15–16 (Year 11) | ✅ Live — `marts.fact_ks4_performance` |
+| **Sixth form** | A levels, applied general, tech levels | KS5 (16–18) | 17–18 (Year 12–13) | ⏳ Not ingested — placeholders in §4 |
+| **Other** | Non-exam context displayed alongside results | n/a | n/a | ✅ Live — various marts |
+
+Not covered (not displayed today, candidates for future "Other"/Primary):
+EYFS Good Level of Development, Year 1 Phonics check, Year 4 Multiplication
+Tables Check, KS1 assessments (no longer published at school level by DfE).
+
+## 2. Metric-by-metric mapping (current site)
+
+Every key in `backend/schemas.py` `METRIC_DEFINITIONS` — the single source of
+truth for what the site displays — mapped to its phase group. `category` is
+the existing schema category; source columns are the DfE names used at
+ingestion (legacy performance-tables CSV for KS2, EES for KS4).
+
+### Primary (KS2 SATs)
+
+| Metric key | Category | DfE source column |
+|---|---|---|
+| `rwm_expected_pct` | expected | `PTRWM_EXP` |
+| `reading_expected_pct` | expected | `PTREAD_EXP` |
+| `writing_expected_pct` | expected | `PTWRITTA_EXP` |
+| `maths_expected_pct` | expected | `PTMAT_EXP` |
+| `gps_expected_pct` | expected | `PTGPS_EXP` |
+| `science_expected_pct` | expected | `PTSCITA_EXP` |
+| `rwm_high_pct` | higher | `PTRWM_HIGH` |
+| `reading_high_pct` | higher | `PTREAD_HIGH` |
+| `writing_high_pct` | higher | `PTWRITTA_HIGH` |
+| `maths_high_pct` | higher | `PTMAT_HIGH` |
+| `gps_high_pct` | higher | `PTGPS_HIGH` |
+| `reading_progress` | progress | `READPROG` |
+| `writing_progress` | progress | `WRITPROG` |
+| `maths_progress` | progress | `MATPROG` |
+| `reading_avg_score` | average | `READ_AVERAGE` |
+| `maths_avg_score` | average | `MAT_AVERAGE` |
+| `gps_avg_score` | average | `GPS_AVERAGE` |
+| `rwm_expected_boys_pct` | gender | `PTRWM_EXP_B` |
+| `rwm_expected_girls_pct` | gender | `PTRWM_EXP_G` |
+| `rwm_high_boys_pct` | gender | `PTRWM_HIGH_B` |
+| `rwm_high_girls_pct` | gender | `PTRWM_HIGH_G` |
+| `rwm_expected_disadvantaged_pct` | equity | `PTRWM_EXP_FSM6CLA1A` |
+| `rwm_expected_non_disadvantaged_pct` | equity | `PTRWM_EXP_NotFSM6CLA1A` |
+| `disadvantaged_gap` | equity | `DIFFN_RWM_EXP` |
+| `reading_absence_pct` | absence | `PTREAD_AT` |
+| `gps_absence_pct` | absence | `PTGPS_AT` |
+| `maths_absence_pct` | absence | `PTMAT_AT` |
+| `writing_absence_pct` | absence | `PTWRITTA_AD` |
+| `science_absence_pct` | absence | `PTSCITA_AD` |
+| `rwm_expected_3yr_pct` | trends | `PTRWM_EXP_3YR` |
+| `reading_avg_3yr` | trends | `READ_AVERAGE_3YR` |
+| `maths_avg_3yr` | trends | `MAT_AVERAGE_3YR` |
+
+The absence metrics measure absence *from KS2 tests*, so they belong to
+Primary even though they are not attainment scores. National comparators for
+this group come from `marts.fact_ks2_national_averages`.
+
+### Secondary (KS4 / GCSE)
+
+| Metric key | Category | EES source column |
+|---|---|---|
+| `attainment_8_score` | gcse | `attainment8_average` |
+| `progress_8_score` | gcse | `progress8_average` |
+| `english_maths_standard_pass_pct` | gcse | `engmath_94_percent` |
+| `english_maths_strong_pass_pct` | gcse | `engmath_95_percent` |
+| `ebacc_entry_pct` | gcse | `ebacc_entering_percent` |
+| `ebacc_standard_pass_pct` | gcse | `ebacc_94_percent` |
+| `ebacc_strong_pass_pct` | gcse | `ebacc_95_percent` |
+| `ebacc_avg_score` | gcse | `ebacc_aps_average` |
+| `gcse_grade_91_pct` | gcse | `gcse_91_percent` |
+
+Also stored in `marts.fact_ks4_performance` (and `fact_performance`) but not
+yet in `METRIC_DEFINITIONS` — Secondary group members when surfaced:
+`progress_8_lower_ci`, `progress_8_upper_ci`, `progress_8_english`,
+`progress_8_maths`, `progress_8_ebacc`, `progress_8_open`,
+`prior_attainment_avg` (KS2 baseline of the GCSE cohort), `sen_pct`.
+
+### Sixth form (KS5)
+
+No metrics today. The secondary school detail view renders a static note
+("Post-16 destination data coming soon") when the school has a sixth form.
+Placeholders for ingestion are specified in §4.
+
+### Other (non-exam context)
+
+Displayed alongside results but not tied to any assessment:
+
+| Metric key / surface | Category | Source |
+|---|---|---|
+| `disadvantaged_pct` | context | KS2 CSV `PTFSM6CLA1A` |
+| `eal_pct` | context | KS2 CSV `PTEALGRP2` |
+| `sen_support_pct` | context | KS2 CSV `PSENELK` (KS4 fallback `sen_no_ehcp_pupil_percent`) |
+| `stability_pct` | context | KS2 CSV `PTMOBN` |
+| Ofsted grades incl. `sixth_form_provision` / `rc_sixth_form` | — | `marts.fact_ofsted_inspection` |
+| Admissions (offers, oversubscription) | — | `marts.fact_admissions` |
+| Finance (per-pupil spend, cost shares) | — | `marts.fact_finance` |
+| Deprivation (IDACI) | — | `marts.fact_deprivation` |
+| Pupil characteristics (census) | — | `marts.fact_pupil_characteristics` |
+
+Note: the context metrics are cohort characteristics of the KS2 cohort at
+source, but they are presented (and should stay presented) as school-level
+context, so they group as Other, not Primary.
+
+## 3. Sixth-form separation
+
+### Definition (authoritative)
+
+> A school **has a sixth form** iff GIAS `OfficialSixthForm (name)` =
+> `"Has a sixth form"` for its URN.
+
+GIAS values are `Has a sixth form`, `Does not have a sixth form`, and
+`Not applicable` / blank. `Not applicable` (nurseries, primaries, PRUs) maps
+to **false**. This field is the DfE's registry flag, updated continuously,
+and is the only source that correctly classifies:
+
+- 16–19 sixth-form colleges and UTCs (age ranges like `14-19`, `16-19` that
+  the current substring heuristic misclassifies as *no* sixth form);
+- schools whose statutory age range extends to 18 on paper but which have no
+  registered post-16 provision.
+
+### Pipeline change (implemented 2026-07-07)
+
+1. `stg_gias_establishments.sql`: add
+   `"OfficialSixthForm (name)" as official_sixth_form`.
+2. `dim_school.sql` (+ `models.py` `DimSchool`, `_marts_schema.yml`): add
+   `has_sixth_form boolean` = `official_sixth_form = 'Has a sixth form'`.
+3. Expose `has_sixth_form` on the school API payloads.
+
+Implemented in `feat/gias-sixth-form-flag` — see
+`docs/superpowers/plans/2026-07-07-gias-sixth-form-flag.md`.
+
+### Current heuristic — audit of `age_range` ~ "18" sites
+
+All must migrate to the `has_sixth_form` flag once exposed:
+
+| Site | Current behaviour |
+|---|---|
+| `backend/app.py:419-422` | `/api/schools?has_sixth_form=yes\|no` filters on `age_range.str.contains("18")` |
+| `nextjs-app/components/SecondarySchoolDetailView.tsx:101` | "Sixth form" badge + coming-soon note from `age_range?.includes('18')` |
+| `nextjs-app/components/FilterBar.tsx:370-372` | Filter labels hard-code "(11-18)" / "(11-16)" — labels should drop the age-range parenthetical since sixth form ≠ age range |
+
+Fallback rule: if GIAS is blank for a URN (rare; new establishments), fall
+back to the age-range heuristic and log the URN.
+
+### UI separation rules
+
+- **School page**: schools with `has_sixth_form = true` show a Sixth form
+  results section (placeholder until KS5 data lands); schools without never
+  show it. Badge on the header as today, but driven by the flag.
+- **Search/rankings filter**: "With sixth form" / "Without sixth form" uses
+  the flag; applies to secondary and all-through phases.
+- **Comparison**: when comparing a with-sixth-form school against one
+  without, the Sixth form group renders "No sixth form" for the latter
+  rather than blank cells, making the structural difference explicit.
+
+## 4. Sixth form placeholders — future KS5 ingestion spec
+
+Source: DfE "A level and other 16 to 18 results" (EES, preferred — matches
+the KS4 EES tap) or legacy performance-tables `england_ks5final.csv`.
+Column names below are from the legacy KS5 CSV; verify against the EES
+release chosen at ingestion time.
+
+| Proposed metric key | Name | Legacy source column | Type |
+|---|---|---|---|
+| `alevel_aps_per_entry` | A level average points per entry | `TALLPPE_ALEV_1618` | score |
+| `alevel_avg_grade` | A level average grade (e.g. B-) | `TALLPPEGRD_ALEV_1618` | grade |
+| `academic_aps_per_entry` | Academic qualifications APS per entry | `TALLPPE_ACAD_1618` | score |
+| `applied_general_aps_per_entry` | Applied general APS per entry | `TALLPPE_AGEN_1618` | score |
+| `tech_level_aps_per_entry` | Tech level APS per entry | `TALLPPE_TLEV_1618` | score |
+| `english_progress_1618` | English progress (16–18, unfinished GCSE 4+) | `PROGENG_1618` | score |
+| `maths_progress_1618` | Maths progress (16–18) | `PROGMAT_1618` | score |
+| `ks5_cohort_size` | Students at end of 16–18 study | `TALLPUP_1618` | count |
+| `alevel_3plus_aab_pct` | % achieving AAB+ in ≥2 facilitating subjects | `TAAB2FAC_1618` | percentage |
+| `ks5_retention_pct` | Retention (completed main programme) | study-programme retention measure | percentage |
+| `ks5_destinations_pct` | Sustained education/employment destination | 16–18 destination measures dataset | percentage |
+
+Proposed landing shape mirrors KS4: `stg_ees_ks5.sql` →
+`int_ks5_with_lineage.sql` → `marts.fact_ks5_performance` (one row per URN
+per year), joined into `fact_performance`, with a `category: "sixth_form"`
+(or `"alevel"`) block added to `METRIC_DEFINITIONS`.
+
+## 5. Out of scope
+
+- Any implementation (pipeline, API, or UI changes) — this is the taxonomy
+  reference; implementation work items are §3 "Pipeline change", the
+  heuristic migration audit, and §4 ingestion, each to be planned separately.
+- Middle schools (deemed secondary/primary): they follow the assessment-based
+  grouping automatically — no special casing.
+- Independent schools: no DfE performance data published; unaffected.

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

@@ -0,0 +1,46 @@
+/**
+ * SecondarySchoolRow — sixth-form tag must come from the GIAS
+ * has_sixth_form flag, not the age_range-contains-"18" heuristic.
+ */
+
+import '@testing-library/jest-dom';
+import { render, screen } from '@testing-library/react';
+import { SecondarySchoolRow } from '@/components/SecondarySchoolRow';
+import type { School } from '@/lib/types';
+
+const base = {
+  urn: 100002,
+  school_name: 'Beta Sixth Form College',
+  local_authority: 'Testshire',
+  school_type: 'Academy',
+  phase: 'Secondary',
+  gender: 'Mixed',
+  attainment_8_score: 50.0,
+} as unknown as School;
+
+describe('SecondarySchoolRow sixth-form tag', () => {
+  it('shows the tag for a 16-19 college with the GIAS flag set', () => {
+    render(
+      <SecondarySchoolRow
+        school={{ ...base, age_range: '16-19', has_sixth_form: true }}
+      />,
+    );
+    expect(screen.getByText('Sixth form')).toBeInTheDocument();
+  });
+
+  it('hides the tag for an 11-18 school without a registered sixth form', () => {
+    render(
+      <SecondarySchoolRow
+        school={{ ...base, age_range: '11-18', has_sixth_form: false }}
+      />,
+    );
+    expect(screen.queryByText('Sixth form')).not.toBeInTheDocument();
+  });
+
+  it('hides the tag when the flag is missing (pipeline not yet re-run)', () => {
+    render(
+      <SecondarySchoolRow school={{ ...base, age_range: '11-18' }} />,
+    );
+    expect(screen.queryByText('Sixth form')).not.toBeInTheDocument();
+  });
+});

nextjs-app/components/FilterBar.tsx

@@ -368,8 +368,8 @@ export function FilterBar({
                     disabled={isPending}
                   >
                     <option value="">With or without sixth form</option>
-                    <option value="yes">With sixth form (11-18)</option>
-                    <option value="no">Without sixth form (11-16)</option>
+                    <option value="yes">With sixth form</option>
+                    <option value="no">Without sixth form</option>
                   </select>
 
                   {admissionsPolicyOptions.length > 0 && (

nextjs-app/components/SecondarySchoolDetailView.tsx

@@ -98,7 +98,8 @@ export function SecondarySchoolDetailView({
 
   const secondaryAvg = nationalAvg?.secondary ?? {};
 
-  const hasSixthForm = schoolInfo.age_range?.includes('18') ?? false;
+  // GIAS OfficialSixthForm flag; missing (pipeline not yet re-run) => false.
+  const hasSixthForm = schoolInfo.has_sixth_form ?? false;
   const hasFinance = finance != null && finance.per_pupil_spend != null;
   const hasDeprivation = deprivation != null && deprivation.idaci_decile != null;
   const hasLocation = schoolInfo.latitude != null && schoolInfo.longitude != null;

nextjs-app/components/SecondarySchoolRow.tsx

@@ -23,7 +23,8 @@ function detectAdmissionsTag(school: School): string | null {
 }
 
 function hasSixthForm(school: School): boolean {
-  return school.age_range?.includes('18') ?? false;
+  // GIAS OfficialSixthForm flag; missing (pipeline not yet re-run) => false.
+  return school.has_sixth_form ?? false;
 }
 
 interface SecondarySchoolRowProps {

nextjs-app/lib/types.ts

@@ -17,6 +17,7 @@ export interface School {
   school_type_code: string | null;
   religious_denomination: string | null;
   age_range: string | null;
+  has_sixth_form?: boolean | null;
 
   // Address
   address1: string | null;

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

@@ -33,6 +33,7 @@ class GIASEstablishmentsStream(Stream):
         th.Property("EstablishmentName", th.StringType),
         th.Property("TypeOfEstablishment (name)", th.StringType),
         th.Property("PhaseOfEducation (name)", th.StringType),
+        th.Property("OfficialSixthForm (name)", th.StringType),
         th.Property("LA (code)", th.StringType),
         th.Property("LA (name)", th.StringType),
         th.Property("EstablishmentNumber", th.StringType),

pipeline/transform/models/marts/_marts_schema.yml

@@ -16,6 +16,17 @@ models:
         tests:
           - not_null:
               severity: warn
+      - name: has_sixth_form
+        description: >
+          Authoritative sixth-form flag from GIAS OfficialSixthForm.
+          "Has a sixth form" => true; "Does not have a sixth form" and
+          "Not applicable" => false; blank GIAS value falls back to
+          statutory_high_age >= 18. Replaces the age_range-contains-"18"
+          heuristic (spec 2026-07-07 §3).
+        tests:
+          - not_null
+          - accepted_values:
+              values: [true, false]
       - name: status
         tests:
           - accepted_values:

pipeline/transform/models/marts/dim_school.sql

@@ -52,6 +52,17 @@ select
     s.religious_character,
     s.gender,
     s.statutory_low_age || '-' || s.statutory_high_age as age_range,
+    -- Authoritative sixth-form flag (spec §3): GIAS OfficialSixthForm.
+    -- "Not applicable" (nurseries, primaries, PRUs) => false. Blank GIAS
+    -- value (rare, new establishments) falls back to the statutory age range.
+    -- lower(trim()) guards against casing/whitespace variants in raw GIAS
+    -- data, same as the phase derivation above — an unmatched variant would
+    -- otherwise silently fall through to the age-range fallback.
+    case
+        when lower(trim(s.official_sixth_form)) = 'has a sixth form' then true
+        when lower(trim(s.official_sixth_form)) in ('does not have a sixth form', 'not applicable') then false
+        else coalesce(s.statutory_high_age >= 18, false)
+    end as has_sixth_form,
     s.capacity,
     s.total_pupils,
     concat_ws(' ', s.head_title, s.head_first_name, s.head_last_name) as headteacher_name,

pipeline/transform/models/staging/stg_gias_establishments.sql

@@ -14,6 +14,7 @@ renamed as (
         "EstablishmentName"                             as school_name,
         "TypeOfEstablishment (name)"                    as school_type,
         "PhaseOfEducation (name)"                       as phase,
+        nullif(trim("OfficialSixthForm (name)"), '')    as official_sixth_form,
         "Gender (name)"                                 as gender,
         "ReligiousCharacter (name)"                     as religious_character,
         "AdmissionsPolicy (name)"                       as admissions_policy,