Make aggregate return an AsyncIterator, other clean up

CHANGELOG.md

@@ -15,18 +15,21 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Changed
 
+- Improved interruption handling to prevent bots from repeating themselves.
+  LLM services that return multiple sentences in a single response (e.g.,
+  `GoogleLLMService`) are now split into individual sentences before being sent
+  to TTS. This ensures interruptions occur at sentence boundaries, preventing
+  the bot from repeating content after being interrupted during long responses.
+
 - Text Aggregation Improvements:
 
-  - Updated `LLMTextProcessor` and `TTSService` to normalize text input by
-    splitting into individual characters before aggregation. This ensures proper
-    sentence boundary detection when LLMs return multiple sentences in a single
-    chunk (e.g., Google Gemini).
-  - All text aggregators now properly support character-by-character streaming
-    input.
+  - **Breaking Change**: `BaseTextAggregator.aggregate()` now returns
+    `AsyncIterator[Aggregation]` instead of `Optional[Aggregation]`. This
+    enables the aggregator to return multiple results based on the provided
+    text.
   - Refactored text aggregators to use inheritance: `SkipTagsAggregator` and
     `PatternPairAggregator` now inherit from `SimpleTextAggregator`, reusing
-    its lookahead-based sentence detection logic via
-    `_check_sentence_with_lookahead()`.
+    the base class's sentence detection logic.
 
 - Updated `AICFilter` to use Quail STT as the default model
   (`AICModelType.QUAIL_STT`). Quail STT is optimized for human-to-machine
@@ -54,6 +57,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Fixed an issue where `LLMTextFrame.skip_tts` was being overwritten by LLM
   services.
 
+- Fixed sentence aggregation to correctly handle ambiguous punctuation in
+  streaming text, such as currency ("$29.95") and abbreviations ("Mr. Smith").
+
+- Fixed bug in `PatternPairAggregator` where pattern handlers could be called
+  multiple times for `KEEP` or `AGGREGATE` patterns.
+
 - Fixed an issue in `SarvamTTSService` where the last sentence was not being
   spoken. Now, audio is flushed when the TTS services receives the
   `LLMFullResponseEndFrame` or `EndFrame`.
@@ -66,10 +75,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   voice-ui-kit's conversational panel rending of the LLM output after a
   function call.
 
-- Fixed a bug in `PatternPairAggregator` where pattern handlers could be called
-  multiple times for patterns with `MatchAction.KEEP` or `MatchAction.AGGREGATE`
-  actions.
-
 ## [0.0.96] - 2025-11-26 🦃 "Happy Thanksgiving!" 🦃
 
 ### Added