feat(audio): add pluggable audio preprocessing and denoising layer before STT

- Add audio_enhancer module with 60s timeout, zero-transcoding default, and fail-soft fallback
- Persist enhanced audio in daily folders with _enhanced suffix and emit audio.enhance.result event
- Connect audio enhancer to transcribe_multi and transcribe in stt.py
- Forward message_id and trace_id from handlers
- Ensure consensus_text fallback persistence and remove scenario leakage in nlu.py
- Add test_enhancer.py unit suite and update smoke_test.py

bot/app/handlers/__init__.py

@@ -104,6 +104,7 @@ async def handle_message(ctx: BotContext, chat_id: int, message: dict) -> None:
                 mime_type=audio_media.get("mime_type"),
                 filename=audio_media.get("file_name"),
                 trace_id=trace_id,
+                message_id=message_id,
             )
         except Exception as exc:
             detail = "هوش مصنوعی تنظیم نشده" if "not configured" in str(exc) else str(exc)[:200]
@@ -421,7 +422,9 @@ async def _handle_ambiguity_user_reply(
             audio_media = message.get("voice") or message.get("audio")
             audio_bytes = await ctx.bale.download_file(audio_media["file_id"])
             obs.save_voice(trace_id, incoming_msg_id or 0, audio_bytes)
-            text = await transcribe(settings, audio_bytes, trace_id=trace_id)
+            text = await transcribe(
+                settings, audio_bytes, trace_id=trace_id, message_id=incoming_msg_id
+            )
         except Exception:
             text = ""