fix(api): match missing-column fallbacks on the DBAPI error, not the statement

str(ProgrammingError) embeds the full SQL, which contains every column
name — the substring check matched any error and could take the wrong
retry branch. Parse the missing column from exc.orig instead.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

backend/data_loader.py

@@ -4,6 +4,7 @@ Provides efficient queries with caching.
 """
 
 import logging
+import re
 
 import pandas as pd
 import numpy as np
@@ -291,13 +292,28 @@ _GIAS_CODE_COLUMN_NAMES = (
     "admissions_policy_code",
 )
 
+_MISSING_COLUMN_RE = re.compile(r'column "?(?:s\.)?(\w+)"? does not exist')
+
+
+def _missing_column_name(exc: Exception) -> Optional[str]:
+    """Name of the missing column from a psycopg2 UndefinedColumn error.
+
+    Inspects exc.orig (the DBAPI error), whose message names only the
+    offending column — str(exc) also embeds the full SQL statement, which
+    contains every column name and therefore must not be matched against.
+    """
+    orig = getattr(exc, "orig", None)
+    match = _MISSING_COLUMN_RE.search(str(orig) if orig is not None else str(exc))
+    return match.group(1) if match else None
+
 
 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 any(col in str(exc) for col in _GIAS_CODE_COLUMN_NAMES):
+        missing = _missing_column_name(exc)
+        if missing in _GIAS_CODE_COLUMN_NAMES:
             logging.getLogger(__name__).warning(
                 "marts predate the GIAS code migration — falling back to "
                 "legacy name-column query: %s",
@@ -308,7 +324,7 @@ def load_school_data_as_dataframe() -> pd.DataFrame:
             except Exception as exc2:
                 print(f"Warning: Could not load school data from marts: {exc2}")
                 return pd.DataFrame()
-        elif "has_sixth_form" in str(exc):
+        elif missing == "has_sixth_form":
             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",