Add text chunking functionality to chat endpoint

- Introduced SentenceTextChunker and SentenceTextChunkerConfig for improved text processing in chat responses.
- Updated chat endpoint to conditionally use text chunking based on the new 'useTextChunk' parameter from the request.
- Enhanced logging to include 'useTextChunk' status and adjusted text delta handling to support chunked responses.
- Modified ProcessRequest_chat model to include 'useTextChunk' field for request handling.
- Added unit tests for SentenceTextChunker to ensure correct chunking behavior and edge case handling.

test/test_text_chunker.py

@@ -0,0 +1,57 @@
+from src.voice.text_chunker import SentenceTextChunker, SentenceTextChunkerConfig
+
+
+def test_chinese_sentence_chunks_wait_for_lookahead():
+    chunker = SentenceTextChunker()
+    chunks = []
+
+    for token in ["你好", "世界", "。", "下一", "句话", "。"]:
+        chunks.extend(chunker.feed(token))
+
+    assert chunks == ["你好世界。"]
+    assert chunker.flush() == "下一句话。"
+
+
+def test_flush_returns_pending_text():
+    chunker = SentenceTextChunker()
+
+    assert chunker.feed("还没有句号") == []
+    assert chunker.flush() == "还没有句号"
+    assert chunker.flush() is None
+
+
+def test_decimal_point_does_not_split_sentence():
+    chunker = SentenceTextChunker()
+
+    chunks = chunker.feed("价格是29.95元。下一句")
+
+    assert chunks == ["价格是29.95元。"]
+    assert chunker.flush() == "下一句"
+
+
+def test_soft_break_after_max_chars():
+    chunker = SentenceTextChunker(
+        SentenceTextChunkerConfig(
+            min_chars=1,
+            max_chars=12,
+            use_soft_breaks=True,
+        )
+    )
+
+    chunks = chunker.feed("这是一段比较长的话，需要先切一下继续播放")
+
+    assert chunks == ["这是一段比较长的话，"]
+    assert chunker.flush() == "需要先切一下继续播放"
+
+
+def test_can_disable_soft_breaks():
+    chunker = SentenceTextChunker(
+        SentenceTextChunkerConfig(
+            min_chars=1,
+            max_chars=12,
+            use_soft_breaks=False,
+        )
+    )
+
+    assert chunker.feed("这是一段比较长的话，需要先切一下继续播放") == []
+    assert chunker.flush() == "这是一段比较长的话，需要先切一下继续播放"