fix(places): phase links must stay in their own namespace

Every place page built its phase links as /schools/[slug]/[phase], the
shape that belongs to towns alone.

On an authority page that pointed into the town namespace. For 87 of the
151 authorities the target does not exist and the link 404s; for the
other 64 it resolves to the town of the same name — a different set of
schools, which is precisely the near-duplicate the two namespaces were
introduced to prevent. On an outcode page it 404s outright.

Two causes behind it, both a rule written twice and inherited by only
one of the places that needed it.

The authority phase route was in the spec and dropped by the plan, which
built the three bare routes and no fourth. The sitemap is generated from
the place registry, which was right about them all along, so 302
authority phase URLs have been submitted to Google and every one 404s.
Adding the route makes the sitemap true and serves a real query —
admissions are authority-run, so "primary schools in Kent" is how a
parent searches before they have settled on a town.

The outcode variants were the opposite: the registry computed phases for
outcodes although the spec gives them no route, and the sitemap knew to
skip them while the API did not. The registry now decides alone, and the
sitemap's duplicate of that rule is gone.

Also: an authority under the five-school threshold has no page, so the
API sends a null slug for it and the page names it without linking.
Two English authorities are in that position. It was unreachable in
today's data — verified across the EC and TR outcodes — but the thin
place redirect would have sent a reader to a 404 the year it isn't.

The e2e journey now walks every /schools link a page of each family
emits and requires a 200, which is the check that was missing.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015mWQnpye9F299NVRCCSRvj

backend/app.py

@@ -222,10 +222,10 @@ def _place_sitemap_rows(kinds: tuple[str, ...]) -> list[str]:
         if p.kind not in kinds:
             continue
         rows.append(_url_element(BASE_URL + _place_url(p)))
-        # Outcodes carry no phase variants: nobody searches "primary schools
-        # in SW11", so the routes do not exist to submit.
-        if p.kind == "outcode":
-            continue
+        # Which phases a place publishes is the registry's decision alone —
+        # outcodes report none, because the spec gives them no phase route.
+        # Repeating that rule here was how the page and the sitemap came to
+        # disagree about which URLs exist.
         for phase in ("primary", "secondary"):
             if p.publishes_phase(phase):
                 rows.append(_url_element(f"{BASE_URL}{_place_url(p)}/{phase}"))
@@ -1200,7 +1200,8 @@ async def get_place(request: Request, kind: str, slug: str,
     if kind not in VALID_PLACE_KINDS:
         raise HTTPException(status_code=404, detail="No such place")
 
-    place = get_place_registry().get(f"{kind}:{slug}")
+    registry = get_place_registry()
+    place = registry.get(f"{kind}:{slug}")
     if place is None:
         raise HTTPException(status_code=404, detail="No such place")
 
@@ -1240,8 +1241,17 @@ async def get_place(request: Request, kind: str, slug: str,
                   # Every authority the place meaningfully sits in. SW19 is
                   # mostly Merton but partly Wandsworth; naming one asserts
                   # something false.
+                  #
+                  # The slug is null where that authority has no page of its
+                  # own: City of London and the Isles of Scilly hold fewer
+                  # schools than the threshold. Naming them is still right;
+                  # linking them would be a 404.
                   "authorities": [
-                      {"name": name, "slug": _slugify(name), "count": n}
+                      {"name": name,
+                       "slug": (_slugify(name)
+                                if f"authority:{_slugify(name)}" in registry
+                                else None),
+                       "count": n}
                       for name, n in place.authorities
                   ],
                   # Only phases that clear the threshold, so the page links

backend/places.py

@@ -224,7 +224,14 @@ def _outcode(postcode) -> str | None:
 def _outcode_places(df, publishable: set[int]) -> dict[str, Place]:
     """One Place per postcode district clearing the threshold.
 
-    These carry no phase variants: nobody searches "primary schools in SW11".
+    These carry no phase variants: nobody searches "primary schools in SW11",
+    so the spec gives them no /primary or /secondary route. `phase_urns` is
+    left empty rather than computed and then filtered downstream — the
+    registry is the one place that decides which phases a place publishes,
+    and the page links whatever it reports.
+
+    Computing them here put a link to a route that does not exist on every one
+    of the 1,720 outcode pages.
     """
     if "postcode" not in df.columns:
         return {}
@@ -239,8 +246,7 @@ def _outcode_places(df, publishable: set[int]) -> dict[str, Place]:
         authorities = _authorities(group)
         place = Place(kind="outcode", slug=str(oc).lower(), name=str(oc),
                       urns=urns, parent_authority=_parent_authority(authorities),
-                      authorities=authorities,
-                      phase_urns=_phase_urns(group, publishable))
+                      authorities=authorities)
         out[place.key] = place
     return out
 

backend/tests/test_places.py

@@ -389,3 +389,32 @@ def test_the_secondary_threshold_counts_its_own_metric():
     rows = _town(MIN_SCHOOLS, "Brentwood", "Essex")
     reg = build_place_registry(_df(rows))
     assert not reg["town:brentwood"].publishes_phase("secondary")
+
+
+def test_an_outcode_publishes_no_phase_variants():
+    """There is no /schools/near/[outcode]/[phase] route, by design.
+
+    Nobody searches "primary schools in SW11", so the spec gives outcodes no
+    phase variants. The registry computed them anyway, and the place page —
+    which links whatever phases the registry reports — put two 404s on every
+    outcode page in the site.
+
+    This is the single rule now: a kind with no phase route reports no phases,
+    so neither the page nor the sitemap can offer one.
+    """
+    rows = [{"urn": 500000 + i, "school_name": f"SW11 School {i}",
+             "town": "London", "local_authority": "Wandsworth",
+             "postcode": "SW11 1AA"} for i in range(MIN_SCHOOLS + 3)]
+    reg = build_place_registry(_df(rows))
+
+    place = reg["outcode:sw11"]
+    assert place.phase_urns == {}
+    assert not place.publishes_phase("primary")
+    assert not place.publishes_phase("secondary")
+
+
+def test_an_authority_still_publishes_phase_variants():
+    """Authorities keep theirs — "primary schools in Kent" is a real query,
+    and /schools/authority/[la]/[phase] is the route that serves it."""
+    reg = build_place_registry(_df(_town(MIN_SCHOOLS, "Maidstone", "Kent")))
+    assert reg["authority:kent"].publishes_phase("primary")

backend/tests/test_places_api.py

@@ -89,3 +89,51 @@ def test_unknown_place_404s(client):
 
 def test_unknown_kind_404s(client):
     assert client.get("/api/places/planet/mars").status_code == 404
+
+
+def _straddling_df() -> pd.DataFrame:
+    """Eight schools in CM13: six in Essex, which has a page, and two in an
+    authority too small to have one.
+
+    Two, not one: the registry ignores an authority holding a single school in
+    a place, because GIAS carries occasional postcode errors."""
+    df = _schools_df()
+    extra = df.iloc[:2].copy()
+    extra["urn"] = [200000, 200001]
+    extra["school_name"] = ["Scilly School 0", "Scilly School 1"]
+    extra["local_authority"] = "Isles Of Scilly"
+    return pd.concat([df, extra], ignore_index=True)
+
+
+@pytest.fixture()
+def straddling_client(monkeypatch):
+    from backend import app as app_module
+
+    monkeypatch.setattr(app_module, "load_school_data", _straddling_df)
+    monkeypatch.setattr(app_module, "load_latest_school_data", _straddling_df)
+    monkeypatch.setattr(app_module, "_place_registry", None)
+    return TestClient(app_module.app, raise_server_exceptions=False)
+
+
+def test_an_outcode_reports_no_phases_because_it_has_no_phase_route(client):
+    body = client.get("/api/places/outcode/cm13").json()
+    assert body["place"]["phases"] == []
+
+
+def test_an_authority_reports_the_phases_it_publishes(client):
+    body = client.get("/api/places/authority/essex").json()
+    assert body["place"]["phases"] == ["primary"]
+
+
+def test_an_authority_without_a_page_is_named_but_carries_no_slug(straddling_client):
+    """Two English authorities — City of London and the Isles of Scilly — hold
+    fewer than the five schools a page needs, so they have no page.
+
+    Naming them is still right: the page says where the place is. Linking them
+    would not be. A null slug is what tells the page to print the name plainly
+    rather than invent a URL that 404s.
+    """
+    body = straddling_client.get("/api/places/outcode/cm13").json()
+    by_name = {a["name"]: a for a in body["place"]["authorities"]}
+    assert by_name["Essex"]["slug"] == "essex"
+    assert by_name["Isles Of Scilly"]["slug"] is None

backend/tests/test_sitemap.py

@@ -288,3 +288,19 @@ def test_outcodes_get_no_phase_variants(place_sitemaps):
     # Nobody searches "primary schools in CM13"; the routes do not exist.
     xml = place_sitemaps["outcodes-1.xml"]
     assert "/primary" not in xml and "/secondary" not in xml
+
+
+def test_authority_phase_variants_are_submitted_in_their_own_namespace(place_sitemaps):
+    """302 of these were already in the sitemap, and every one 404'd.
+
+    The spec gives authorities a phase route; the plan built the bare
+    authority route and dropped it. Nothing noticed because the sitemap was
+    written from the registry, which was right, while the routes were written
+    by hand. This test fails if the URL ever leaves the sitemap; the e2e
+    journey fails if the route ever leaves the app.
+    """
+    xml = place_sitemaps["places-1.xml"]
+    assert ("<loc>https://www.schoolcompare.co.uk"
+            "/schools/authority/essex/primary</loc>") in xml
+    # And never in the town namespace, which is a different set of schools.
+    assert "/schools/essex/primary" not in xml