fix(gateway): bypass text batching when delay is 0 (#6996)

The text batching feature routes TEXT messages through
asyncio.create_task() + asyncio.sleep(delay). Even with delay=0,
the task fires asynchronously and won't complete before synchronous
test assertions. This broke 33 tests across Discord, Matrix, and
WeCom adapters.

When _text_batch_delay_seconds is 0 (the test fixture setting),
dispatch directly to handle_message() instead of going through
the async batching path. This preserves the pre-batching behavior
for tests while keeping batching active in production (default
delay 0.6s).

gateway/platforms/discord.py

@@ -2474,7 +2474,7 @@ class DiscordAdapter(BasePlatformAdapter):
 
         # Only batch plain text messages — commands, media, etc. dispatch
         # immediately since they won't be split by the Discord client.
-        if msg_type == MessageType.TEXT:
+        if msg_type == MessageType.TEXT and self._text_batch_delay_seconds > 0:
             self._enqueue_text_event(event)
         else:
             await self.handle_message(event)

gateway/platforms/matrix.py

@@ -1101,7 +1101,7 @@ class MatrixAdapter(BasePlatformAdapter):
         self._background_read_receipt(room.room_id, event.event_id)
 
         # Only batch plain text messages — commands dispatch immediately.
-        if msg_type == MessageType.TEXT:
+        if msg_type == MessageType.TEXT and self._text_batch_delay_seconds > 0:
             self._enqueue_text_event(msg_event)
         else:
             await self.handle_message(msg_event)

gateway/platforms/wecom.py

@@ -531,7 +531,7 @@ class WeComAdapter(BasePlatformAdapter):
 
         # Only batch plain text messages — commands, media, etc. dispatch
         # immediately since they won't be split by the WeCom client.
-        if message_type == MessageType.TEXT:
+        if message_type == MessageType.TEXT and self._text_batch_delay_seconds > 0:
             self._enqueue_text_event(event)
         else:
             await self.handle_message(event)