fix: sanitize lone surrogate chars in stored data + backfill script

Upstream API records may contain lone surrogate chars (emoji fragments)
that break SQLite/MySQL utf-8 encoding. Now sanitized to U+FFFD before
storage. Includes backfill_customers.py for full customer backfill.

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

yunke-server/app/storage/repos.py

@@ -211,9 +211,29 @@ def _build_column_values(
     # truth.
     if "raw_json" in col_names and "raw_json" not in values:
         values["raw_json"] = rec
+    # Sanitize lone surrogate chars (e.g. \udf1e from emoji fragments in the
+    # upstream API) that break SQLite/MySQL UTF-8 encoding. Replaces them with
+    # the Unicode replacement character (U+FFFD).
+    for k, v in values.items():
+        values[k] = _sanitize_surrogates(v)
     return values
 
 
+def _sanitize_surrogates(obj: Any) -> Any:
+    """Recursively remove lone surrogate characters from strings/dicts/lists."""
+    if isinstance(obj, str):
+        try:
+            obj.encode("utf-8")  # fast-path: clean string, no copy
+            return obj
+        except UnicodeEncodeError:
+            return obj.encode("utf-8", "replace").decode("utf-8")
+    if isinstance(obj, dict):
+        return {k: _sanitize_surrogates(v) for k, v in obj.items()}
+    if isinstance(obj, list):
+        return [_sanitize_surrogates(v) for v in obj]
+    return obj
+
+
 def _build_upsert_stmt(
     model: type[DeclarativeBase], values: dict[str, Any], dialect_name: str
 ) -> sa.Insert: