Add trace logging for previous_response_id decisions and fix example

Add detailed trace-level logging to _apply_previous_response_optimization
showing why the optimization was applied or fell back to full context,
including the relevant data for debugging.

Use append_to_context=False for the filler TTSSpeakFrame in the
function-calling example to avoid altering the conversation history
and breaking the previous_response_id prefix match.

examples/foundational/14-function-calling-openai-responses.py

@@ -86,7 +86,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     @llm.event_handler("on_function_calls_started")
     async def on_function_calls_started(service, function_calls):
-        await tts.queue_frame(TTSSpeakFrame("Let me check on that."))
+        # Avoid appending this filler message to the LLM context — it would
+        # alter the conversation history and prevent
+        # OpenAIResponsesLLMService's previous_response_id optimization from
+        # matching, forcing a full context resend.
+        await tts.queue_frame(TTSSpeakFrame("Let me check on that.", append_to_context=False))
 
     weather_function = FunctionSchema(
         name="get_current_weather",