fix: Heading detection allows digit-start (e.g. "5. Soziale Medien")

Headings starting with numbers (numbered sections like "5. Soziale
Medien", "6. Analyse-Tools") were not detected because the check
required stripped[0].isupper(). Now also accepts stripped[0].isdigit().

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

backend-compliance/compliance/api/agent_doc_check_routes.py

@@ -377,7 +377,7 @@ def _split_into_sections(text: str, parent_label: str, url: str) -> list[dict]:
             5 < len(stripped) < 80
             and not stripped.endswith(".")
             and not stripped.endswith(",")
-            and stripped[0].isupper()
+            and (stripped[0].isupper() or stripped[0].isdigit())
         )
         classified = _classify_section(stripped) if is_heading else None
         is_real_heading = is_heading and classified is not None