Merge pull request #153 from pipecat-ai/expose-llm-messages

aggregators: expose LLM messages

CHANGELOG.md

@@ -5,6 +5,13 @@ All notable changes to **pipecat** will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [Unreleased]
+
+### Changed
+
+- `LLMUserResponseAggregator` and `LLMAssistantResponseAggregator` internal
+  messages are now exposed through the `messages` property.
+
 ## [0.0.18] - 2024-05-20
 
 ### Fixed

src/pipecat/processors/aggregators/llm_response.py

@@ -45,6 +45,14 @@ def __init__(
         # Reset our accumulator state.
         self._reset()
 
+    @property
+    def messages(self):
+        return self._messages
+
+    @property
+    def role(self):
+        return self._role
+
     #
     # Frame processor
     #