fix(ks2): make reimport async with polling to avoid HTTP timeout

The geocoding pass over ~15k schools takes longer than any reasonable
HTTP timeout. New approach:
- POST /api/admin/reimport-ks2 starts migration in background thread,
  returns {"status":"started"} immediately
- GET /api/admin/reimport-ks2/status returns {running, done}
- ks2.py polls status every 30s (max 2h) before returning
- Kestra flow timeout bumped to PT2H

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

integrator/scripts/sources/ks2.py

@@ -10,10 +10,14 @@ The CSV files must already be present in the data volume under
   /data/{year}/england_ks2final.csv
 (populated at deploy time from the repo's data/ directory).
 """
-import sys
+import time
 import requests
 from config import BACKEND_URL, ADMIN_API_KEY
 
+HEADERS = {"X-API-Key": ADMIN_API_KEY}
+POLL_INTERVAL = 30   # seconds between status checks
+MAX_WAIT = 7200      # 2 hours
+
 
 def download():
     """No download step — CSVs are shipped with the repo."""
@@ -22,18 +26,33 @@ def download():
 
 
 def load():
-    """Trigger full KS2 re-import via the backend admin endpoint (with geocoding)."""
-    url = f"{BACKEND_URL}/api/admin/reimport-ks2?geocode=true"
-    print(f"POST {url}")
-    resp = requests.post(
-        url,
-        headers={"X-API-Key": ADMIN_API_KEY},
-        timeout=900,  # migration can take ~10 minutes
-    )
+    """Trigger full KS2 re-import and poll until complete."""
+    start_url = f"{BACKEND_URL}/api/admin/reimport-ks2?geocode=true"
+    status_url = f"{BACKEND_URL}/api/admin/reimport-ks2/status"
+
+    print(f"POST {start_url}")
+    resp = requests.post(start_url, headers=HEADERS, timeout=30)
     resp.raise_for_status()
-    result = resp.json()
-    print(f"Result: {result}")
-    return result
+    print(f"Started: {resp.json()}")
+
+    print(f"Polling {status_url} every {POLL_INTERVAL}s (max {MAX_WAIT // 60} min)...")
+    elapsed = 0
+    while elapsed < MAX_WAIT:
+        time.sleep(POLL_INTERVAL)
+        elapsed += POLL_INTERVAL
+
+        sr = requests.get(status_url, headers=HEADERS, timeout=15)
+        sr.raise_for_status()
+        state = sr.json()
+        print(f"  [{elapsed // 60}m] {state}")
+
+        if state.get("done"):
+            print("Re-import complete.")
+            return state
+        if not state.get("running"):
+            raise RuntimeError(f"Re-import stopped unexpectedly: {state}")
+
+    raise TimeoutError(f"KS2 re-import did not complete within {MAX_WAIT // 60} minutes")
 
 
 if __name__ == "__main__":