Make the mechanism of adding spaces when concatenating TTS (or speech-to-speech LLM) output text explicit and deterministic, rather than heuristic-based.

This fixes a bug where spaces were sometimes missing from assistant messages in context.
2025-11-10 12:28:40 -05:00
parent c2ce143e6c
commit 913194844e
10 changed files with 113 additions and 44 deletions
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -11,6 +11,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

 - `LivekitFrameSerializer` has been removed. Use `LiveKitTransport` instead.

+### Fixed
+
+- Fixed a bug related to `LLMAssistantAggregator` where spaces were sometimes
+  missing from assistant messages in context.
+
 ## [0.0.93] - 2025-11-07

 ### Added