fix(api): serialize schools that have no performance rows

Schools without KS2/KS4 results (special post-16 institutions, sixth-form
centres, PRUs, new schools) come back from the marts LEFT JOIN with NaN in
every numeric column. school_info passed those raw pandas values straight
into JSONResponse, which renders with allow_nan=False, so the detail
endpoint 500d and the frontend turned that into a 404 on every such SEO
landing page.

Run school_info values through convert_to_native (the same treatment
yearly_data already gets), add backend unit tests plus a pytest step in PR
checks, and an e2e journey that finds a results-less school via the search
API and asserts its page renders.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

backend/app.py

@@ -33,7 +33,7 @@ from .data_loader import (
 )
 from .data_loader import get_data_info as get_db_info
 from .schemas import METRIC_DEFINITIONS, RANKING_COLUMNS, SCHOOL_COLUMNS
-from .utils import clean_for_json
+from .utils import clean_for_json, convert_to_native
 
 # Values to exclude from filter dropdowns (empty strings, non-applicable labels)
 EXCLUDED_FILTER_VALUES = {"", "Not applicable", "Does not apply"}
@@ -582,8 +582,13 @@ async def get_school_details(request: Request, urn: int):
     except Exception:
         pass
 
-    return {
-        "school_info": {
+    # Schools with no performance rows (post-16 institutions, PRUs, new
+    # schools) carry NaN in every LEFT-JOINed numeric column; NaN reaching
+    # JSONResponse raises ValueError, so school_info needs the same
+    # conversion yearly_data gets from clean_for_json.
+    school_info = {
+        k: convert_to_native(v)
+        for k, v in {
             "urn": urn,
             "school_name": latest.get("school_name", ""),
             "local_authority": latest.get("local_authority", ""),
@@ -601,7 +606,11 @@ async def get_school_details(request: Request, urn: int):
             "total_pupils": latest.get("gias_total_pupils"),
             "trust_name": latest.get("trust_name"),
             "gender": latest.get("gender"),
-        },
+        }.items()
+    }
+
+    return {
+        "school_info": school_info,
         "yearly_data": clean_for_json(school_data),
         # Supplementary data (null if not yet populated by Kestra)
         "ofsted": supplementary.get("ofsted"),

backend/tests/test_school_details.py

@@ -0,0 +1,71 @@
+"""Regression tests for GET /api/schools/{urn}.
+
+Schools with no performance rows (special post-16 institutions, sixth-form
+centres, PRUs, brand-new schools) come back from the marts LEFT JOIN with
+NaN in every numeric column. The endpoint must still serialize them — a NaN
+that reaches Starlette's JSONResponse raises ValueError (allow_nan=False)
+and the route 500s, which the frontend then renders as a 404.
+"""
+
+import numpy as np
+import pandas as pd
+import pytest
+from fastapi.testclient import TestClient
+
+
+def _no_results_school_df() -> pd.DataFrame:
+    """One school row as produced by the marts query for a school with no
+    performance data: GIAS/location fields partly populated, every
+    results-linked column NaN (including year)."""
+    return pd.DataFrame(
+        [
+            {
+                "urn": 150275,
+                "school_name": "West London Performing Arts Academy",
+                "phase": "Secondary",
+                "school_type": "Special post 16 institution",
+                "trust_name": None,
+                "religious_denomination": "Does not apply",
+                "gender": None,
+                "age_range": "16-25",
+                "admissions_policy": None,
+                "capacity": np.nan,
+                "gias_total_pupils": np.nan,
+                "headteacher_name": None,
+                "website": None,
+                "ofsted_grade": np.nan,
+                "local_authority": "Ealing",
+                "address": "268 Northfield Avenue, London, W5 4UB",
+                "postcode": "W5 4UB",
+                "latitude": 51.4986,
+                "longitude": -0.3148,
+                "year": np.nan,
+                "total_pupils": np.nan,
+                "eligible_pupils": np.nan,
+                "rwm_expected_pct": np.nan,
+            }
+        ]
+    )
+
+
+@pytest.fixture()
+def client(monkeypatch):
+    from backend import app as app_module
+
+    monkeypatch.setattr(app_module, "load_school_data", _no_results_school_df)
+    monkeypatch.setattr(
+        app_module, "get_supplementary_data", lambda db, urn: {}
+    )
+    return TestClient(app_module.app, raise_server_exceptions=False)
+
+
+def test_school_without_performance_rows_returns_200(client):
+    resp = client.get("/api/schools/150275")
+    assert resp.status_code == 200, resp.text
+
+
+def test_nan_gias_fields_serialize_as_null(client):
+    info = client.get("/api/schools/150275").json()["school_info"]
+    assert info["capacity"] is None
+    assert info["total_pupils"] is None
+    assert info["school_name"] == "West London Performing Arts Academy"