feat(places): /api/places registry and place detail endpoints

The registry is cached for the process and reset by the same admin endpoint
that rebuilds the sitemaps, so places and sitemap always describe the same
corpus rather than drifting apart.

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

backend/app.py

@@ -35,6 +35,7 @@ from .data_loader import (
     search_schools_typesense,
 )
 from .data_loader import get_data_info as get_db_info
+from .places import build_place_registry
 from .schemas import METRIC_DEFINITIONS, RANKING_COLUMNS, SCHOOL_COLUMNS
 from .utils import clean_for_json, convert_to_native
 
@@ -58,6 +59,12 @@ MAX_SLUG_LENGTH = 60
 # regenerate endpoint after a pipeline run.
 _sitemaps: dict[str, str] | None = None
 
+# Built from the same DataFrame the sitemap uses, so places and sitemap can
+# never describe different corpora. Reset by the same admin endpoint.
+_place_registry: dict | None = None
+
+VALID_PLACE_KINDS = ("town", "locality", "authority", "outcode")
+
 
 def _slugify(text: str) -> str:
     text = text.lower()
@@ -170,6 +177,14 @@ SITEMAP_CHUNK_SIZE = 10_000
 SITEMAP_CHILD_PREFIX = "/sitemaps"
 
 
+def get_place_registry() -> dict:
+    """The place registry, built once and cached for the process."""
+    global _place_registry
+    if _place_registry is None:
+        _place_registry = build_place_registry(load_school_data())
+    return _place_registry
+
+
 def _urlset(rows: list[str]) -> str:
     return "\n".join([
         '<?xml version="1.0" encoding="UTF-8"?>',
@@ -1117,6 +1132,62 @@ async def get_rankings(
     }
 
 
+@app.get("/api/places")
+@limiter.limit(f"{settings.rate_limit_per_minute}/minute")
+async def list_places(request: Request):
+    """Every published place. The sitemap and the link modules read this."""
+    registry = get_place_registry()
+    return {"places": [
+        {"kind": p.kind, "slug": p.slug, "name": p.name, "count": len(p.urns)}
+        for p in sorted(registry.values(), key=lambda p: (p.kind, p.slug))
+    ]}
+
+
+@app.get("/api/places/{kind}/{slug}")
+@limiter.limit(f"{settings.rate_limit_per_minute}/minute")
+async def get_place(request: Request, kind: str, slug: str,
+                    phase: Optional[str] = None):
+    """One place: its schools ranked, and its local averages."""
+    if kind not in VALID_PLACE_KINDS:
+        raise HTTPException(status_code=404, detail="No such place")
+
+    place = get_place_registry().get(f"{kind}:{slug}")
+    if place is None:
+        raise HTTPException(status_code=404, detail="No such place")
+
+    df = load_latest_school_data()
+    rows = df[df["urn"].isin(place.urns)]
+
+    if phase:
+        wanted = PHASE_GROUPS.get(phase.lower())
+        if wanted and "phase" in rows.columns:
+            rows = rows[rows["phase"].fillna("").str.lower().isin(wanted)]
+
+    # The metric the page ranks on, which is also the one it averages.
+    metric = "attainment_8_score" if phase == "secondary" else "rwm_expected_pct"
+    if metric in rows.columns:
+        rows = rows.sort_values(metric, ascending=False, na_position="last")
+
+    averages = {
+        m: (None if m not in rows.columns or rows[m].dropna().empty
+            else float(rows[m].dropna().mean()))
+        for m in ("rwm_expected_pct", "attainment_8_score")
+    }
+
+    cols = [c for c in SCHOOL_COLUMNS + ["latitude", "longitude", "phase",
+                                          "rwm_expected_pct", "attainment_8_score",
+                                          "total_pupils"]
+            if c in rows.columns]
+
+    return {
+        "place": {"kind": place.kind, "slug": place.slug, "name": place.name,
+                  "count": len(place.urns),
+                  "parent_authority": place.parent_authority},
+        "schools": clean_for_json(rows[cols]),
+        "averages": averages,
+    }
+
+
 @app.get("/api/data-info")
 @limiter.limit(f"{settings.rate_limit_per_minute}/minute")
 async def get_data_info(request: Request):
@@ -1228,7 +1299,11 @@ async def regenerate_sitemap(
     _: bool = Depends(verify_admin_api_key),
 ):
     """Rebuild and cache the sitemap from current school data. Called by Airflow after data updates."""
-    global _sitemaps
+    global _sitemaps, _place_registry
+    # Places and sitemap are rebuilt together — they read the same marts, and
+    # letting them drift apart would submit URLs for places that no longer
+    # exist.
+    _place_registry = None
     _sitemaps = build_sitemaps()
     n = sum(x.count("<url>") for x in _sitemaps.values())
     return {"status": "ok", "urls": n, "sitemaps": len(_sitemaps)}

backend/tests/test_places_api.py

@@ -0,0 +1,71 @@
+"""Tests for the places API (spec 2026-08-21)."""
+
+import numpy as np
+import pandas as pd
+import pytest
+from fastapi.testclient import TestClient
+
+
+def _schools_df() -> pd.DataFrame:
+    base = {
+        "local_authority": "Essex", "school_type": "Academy",
+        "phase": "Primary", "year": 202425, "ofsted_grade": 2.0,
+        "ofsted_date": None, "attainment_8_score": np.nan,
+        "town": "Brentwood", "postcode": "CM13 1AA", "status": "Open",
+        "address": "1 Test Street", "latitude": 51.6, "longitude": 0.3,
+    }
+    return pd.DataFrame([
+        {**base, "urn": 100000 + i, "school_name": f"Brentwood School {i}",
+         "rwm_expected_pct": 50.0 + i}
+        for i in range(6)
+    ])
+
+
+@pytest.fixture()
+def client(monkeypatch):
+    from backend import app as app_module
+
+    monkeypatch.setattr(app_module, "load_school_data", _schools_df)
+    monkeypatch.setattr(app_module, "load_latest_school_data", _schools_df)
+    monkeypatch.setattr(app_module, "_place_registry", None)
+    return TestClient(app_module.app, raise_server_exceptions=False)
+
+
+def test_registry_lists_each_published_place(client):
+    body = client.get("/api/places").json()
+    slugs = {(p["kind"], p["slug"]) for p in body["places"]}
+    assert ("town", "brentwood") in slugs
+    assert ("authority", "essex") in slugs
+    assert ("outcode", "cm13") in slugs
+
+
+def test_registry_carries_a_count_per_place(client):
+    body = client.get("/api/places").json()
+    town = next(p for p in body["places"] if p["slug"] == "brentwood")
+    assert town["count"] == 6
+
+
+def test_place_detail_returns_its_schools_ranked(client):
+    body = client.get("/api/places/town/brentwood").json()
+    assert body["place"]["name"] == "Brentwood"
+    scores = [s["rwm_expected_pct"] for s in body["schools"]]
+    assert scores == sorted(scores, reverse=True)
+
+
+def test_place_detail_carries_the_local_average(client):
+    body = client.get("/api/places/town/brentwood").json()
+    # 50..55 inclusive
+    assert body["averages"]["rwm_expected_pct"] == pytest.approx(52.5)
+
+
+def test_phase_filter_narrows_the_school_list(client):
+    body = client.get("/api/places/town/brentwood?phase=secondary").json()
+    assert body["schools"] == []
+
+
+def test_unknown_place_404s(client):
+    assert client.get("/api/places/town/atlantis").status_code == 404
+
+
+def test_unknown_kind_404s(client):
+    assert client.get("/api/places/planet/mars").status_code == 404