Fix 06- demo and also fix bugs where dangling sentences wouldn't be spoken

src/dailyai/queue_aggregators.py

@@ -70,6 +70,13 @@ class LLMContextAggregator(AIService):
             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)
 
+    async def finalize(self) -> AsyncGenerator[QueueFrame, None]:
+        # Send any dangling words that weren't finished with punctuation.
+        if self.complete_sentences and self.sentence:
+            self.messages.append({"role": self.role, "content": self.sentence})
+            yield LLMMessagesQueueFrame(self.messages)
+
+
 class LLMUserContextAggregator(LLMContextAggregator):
     def __init__(self,
             messages: list[dict],

src/samples/foundational/06-listen-and-respond.py

@@ -6,7 +6,7 @@ import urllib.parse
 
 from dailyai.services.daily_transport_service import DailyTransportService
 from dailyai.services.azure_ai_services import AzureLLMService, AzureTTSService
-from dailyai.queue_aggregators import LLMContextAggregator
+from dailyai.queue_aggregators import LLMAssistantContextAggregator, LLMContextAggregator, LLMUserContextAggregator
 
 
 async def main(room_url: str, token):
@@ -36,12 +36,8 @@ async def main(room_url: str, token):
             {"role": "system", "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio. Respond to what the user said in a creative and helpful way."},
         ]
 
-        tma_in = LLMContextAggregator(
-            messages, "user", transport.my_participant_id
-        )
-        tma_out = LLMContextAggregator(
-            messages, "assistant", transport.my_participant_id
-        )
+        tma_in = LLMUserContextAggregator(messages, transport.my_participant_id)
+        tma_out = LLMAssistantContextAggregator(messages, transport.my_participant_id)
         await tts.run_to_queue(
             transport.send_queue,
             tma_out.run(