fix(gateway): preserve queued voice events for STT

tests/gateway/test_queue_consumption.py

@@ -10,6 +10,7 @@ from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 
+from gateway.run import _dequeue_pending_event
 from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
@@ -79,6 +80,26 @@ class TestQueueMessageStorage:
         # Should be consumed (cleared)
         assert adapter.get_pending_message(session_key) is None
 
+    def test_dequeue_pending_event_preserves_voice_media_metadata(self):
+        adapter = _StubAdapter()
+        session_key = "telegram:user:voice"
+        event = MessageEvent(
+            text="",
+            message_type=MessageType.VOICE,
+            source=MagicMock(chat_id="123", platform=Platform.TELEGRAM),
+            message_id="voice-q1",
+            media_urls=["/tmp/voice.ogg"],
+            media_types=["audio/ogg"],
+        )
+        adapter._pending_messages[session_key] = event
+
+        retrieved = _dequeue_pending_event(adapter, session_key)
+
+        assert retrieved is event
+        assert retrieved.media_urls == ["/tmp/voice.ogg"]
+        assert retrieved.media_types == ["audio/ogg"]
+        assert adapter.get_pending_message(session_key) is None
+
     def test_queue_does_not_set_interrupt_event(self):
         """The whole point of /queue — no interrupt signal."""
         adapter = _StubAdapter()

tests/gateway/test_stt_config.py

@@ -6,7 +6,9 @@ from unittest.mock import AsyncMock, patch
 import pytest
 import yaml
 
-from gateway.config import GatewayConfig, load_gateway_config
+from gateway.config import GatewayConfig, Platform, load_gateway_config
+from gateway.platforms.base import MessageEvent, MessageType
+from gateway.session import SessionSource
 
 
 def test_gateway_config_stt_disabled_from_dict_nested():
@@ -69,3 +71,46 @@ async def test_enrich_message_with_transcription_avoids_bogus_no_provider_messag
     assert "No STT provider is configured" not in result
     assert "trouble transcribing" in result
     assert "caption" in result
+
+
+@pytest.mark.asyncio
+async def test_prepare_inbound_message_text_transcribes_queued_voice_event():
+    from gateway.run import GatewayRunner
+
+    runner = GatewayRunner.__new__(GatewayRunner)
+    runner.config = GatewayConfig(stt_enabled=True)
+    runner.adapters = {}
+    runner._model = "test-model"
+    runner._base_url = ""
+    runner._has_setup_skill = lambda: False
+
+    source = SessionSource(
+        platform=Platform.TELEGRAM,
+        chat_id="123",
+        chat_type="dm",
+    )
+    event = MessageEvent(
+        text="",
+        message_type=MessageType.VOICE,
+        source=source,
+        media_urls=["/tmp/queued-voice.ogg"],
+        media_types=["audio/ogg"],
+    )
+
+    with patch(
+        "tools.transcription_tools.transcribe_audio",
+        return_value={
+            "success": True,
+            "transcript": "queued voice transcript",
+            "provider": "local_command",
+        },
+    ):
+        result = await runner._prepare_inbound_message_text(
+            event=event,
+            source=source,
+            history=[],
+        )
+
+    assert result is not None
+    assert "queued voice transcript" in result
+    assert "voice message" in result.lower()