little more cleanup

src/dailyai/queue_aggregators.py

@@ -33,7 +33,7 @@ class LLMContextAggregator(AIService):
             role: str,
             bot_participant_id=None,
             complete_sentences=True,
-            pass_through=False):
+            pass_through=True):
         self.messages = messages
         self.bot_participant_id = bot_participant_id
         self.role = role
@@ -42,28 +42,32 @@ class LLMContextAggregator(AIService):
         self.pass_through = pass_through
 
     async def process_frame(self, frame: QueueFrame) -> AsyncGenerator[QueueFrame, None]:
-        # TODO: split up transcription by participant
-        if isinstance(frame, TextQueueFrame):
-
-            # Ignore transcription frames from the bot
-            if isinstance(frame, TranscriptionQueueFrame):
-                if frame.participantId == self.bot_participant_id:
-                    return
-
-            if self.complete_sentences:
-                self.sentence += frame.text
-                if self.sentence.endswith((".", "?", "!")):
-                    self.messages.append({"role": self.role, "content": self.sentence})
-                    self.sentence = ""
-                    yield LLMMessagesQueueFrame(self.messages)
-            else:
-                self.messages.append({"role": self.role, "content": frame.text})
-                yield LLMMessagesQueueFrame(self.messages)
-
-            if self.pass_through:
-                yield frame
-        else:
+        # We don't do anything with non-text frames, pass it along to next in the pipeline.
+        if not isinstance(frame, TextQueueFrame):
             yield frame
+            return
+
+        # The common case for "pass through" is receiving frames from the LLM that we'll
+        # use to update the "assistant" LLM messages, but also passing the text frames
+        # along to a TTS service to be spoken to the user.
+        if self.pass_through:
+            yield frame
+
+        # Ignore transcription frames from the bot
+        if isinstance(frame, TranscriptionQueueFrame):
+            if frame.participantId == self.bot_participant_id:
+                return
+
+        # TODO: split up transcription by participant
+        if self.complete_sentences:
+            self.sentence += frame.text # type: ignore -- the linter thinks this isn't a TextQueueFrame, even though we check it above
+            if self.sentence.endswith((".", "?", "!")):
+                self.messages.append({"role": self.role, "content": self.sentence})
+                self.sentence = ""
+                yield LLMMessagesQueueFrame(self.messages)
+        else:
+            self.messages.append({"role": self.role, "content": frame.text})  # type: ignore -- the linter thinks this isn't a TextQueueFrame, even though we check it above
+            yield LLMMessagesQueueFrame(self.messages)
 
 class LLMUserContextAggregator(LLMContextAggregator):
     def __init__(self,