feat(MAT-46): Extract and post document annotations after voice calls

When a voice call ends and a document was loaded in the room, the bot
now analyzes the transcript for document-specific changes/corrections
and posts them as a structured "Dokument-Aenderungen" message. Returns
nothing if no document changes were discussed.

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

voice.py

@@ -498,6 +498,17 @@ class VoiceSession:
         """Return the call transcript as a list of {role, text} dicts."""
         return list(self._transcript)
 
+    def get_document_context(self) -> str | None:
+        """Return the document context loaded for this call, if any."""
+        return self._document_context
+
+    def get_confluence_page_id(self) -> str | None:
+        """Return the active Confluence page ID, if any."""
+        if not self._document_context:
+            return None
+        ids = re.findall(r'confluence_page_id:(\d+)', self._document_context)
+        return ids[0] if ids else None
+
     async def _run(self):
         try:
             user_id = self.nio_client.user_id