feat(cross-doc): search all texts for all doc_types + misplacement finding

Cross-Document Intelligence: When a doc_type row is empty, searches
ALL other loaded documents for that content. If found (e.g. Widerruf
in AGB), extracts the section, runs the check, AND creates a finding:
"Widerrufsbelehrung in falschem Dokument gefunden — schwer auffindbar"

Keywords for: widerruf, cookie, social_media, impressum, agb, dsb.
Integrated as Step 1c in compliance check pipeline.

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

backend-compliance/compliance/api/agent_compliance_check_routes.py

@@ -178,11 +178,16 @@ async def _run_compliance_check(check_id: str, req: ComplianceCheckRequest):
         # 1. Same URL used for multiple doc_types → split by heading
         # 2. DSI text contains Cookie/Social-Media sections → auto-fill empty rows
         from compliance.services.section_splitter import (
-            split_shared_texts, auto_fill_from_dsi,
+            split_shared_texts, auto_fill_from_dsi, cross_search_documents,
         )
         split_shared_texts(doc_entries, url_text_cache)
         auto_fill_from_dsi(doc_entries)
-        # Refresh doc_texts after splitting
+
+        # Step 1c: Cross-document search — find doc_types in wrong documents
+        _update(check_id, "Dokumente werden uebergreifend durchsucht...")
+        placement_findings = cross_search_documents(doc_entries)
+
+        # Refresh doc_texts after all splitting/searching
         for entry in doc_entries:
             if entry.get("text"):
                 doc_texts[entry["doc_type"]] = entry["text"]
@@ -232,6 +237,13 @@ async def _run_compliance_check(check_id: str, req: ComplianceCheckRequest):
             # Apply profile context filter
             result = _apply_profile_filter(result, profile, doc_type)
 
+            # Add placement findings (doc found in wrong location)
+            for pf in placement_findings:
+                if pf.get("doc_type") == doc_type:
+                    result.checks.insert(0, CheckItem(**{
+                        k: v for k, v in pf.items() if k != "doc_type"
+                    }))
+
             results.append(result)
             total_findings += result.findings_count