diff --git a/src/google/adk/models/lite_llm.py b/src/google/adk/models/lite_llm.py
index 7d13696c96..9f612f3ca6 100644
--- a/src/google/adk/models/lite_llm.py
+++ b/src/google/adk/models/lite_llm.py
@@ -912,7 +912,9 @@ async def _content_to_message_param(
       ):
         reasoning_texts.append(_decode_inline_text_data(part.inline_data.data))
 
-    reasoning_content = _NEW_LINE.join(text for text in reasoning_texts if text)
+    # Preserve reasoning deltas exactly as received. Injecting separators
+    # between fragments can corrupt provider-streamed thinking text.
+    reasoning_content = "".join(text for text in reasoning_texts if text)
     return ChatCompletionAssistantMessage(
         role=role,
         content=final_content,
diff --git a/tests/unittests/models/test_litellm.py b/tests/unittests/models/test_litellm.py
index ace08ad997..addce21800 100644
--- a/tests/unittests/models/test_litellm.py
+++ b/tests/unittests/models/test_litellm.py
@@ -2127,6 +2127,38 @@ async def test_content_to_message_param_assistant_thought_and_content_message():
   assert message["reasoning_content"] == "internal reasoning"
 
 
+@pytest.mark.asyncio
+async def test_content_to_message_param_preserves_chunked_reasoning_deltas():
+  thought_part_1 = types.Part.from_text(text="Hel")
+  thought_part_1.thought = True
+  thought_part_2 = types.Part.from_text(text="lo")
+  thought_part_2.thought = True
+  content = types.Content(
+      role="assistant", parts=[thought_part_1, thought_part_2]
+  )
+
+  message = await _content_to_message_param(content)
+
+  assert message["role"] == "assistant"
+  assert message["content"] is None
+  assert message["reasoning_content"] == "Hello"
+
+
+@pytest.mark.asyncio
+async def test_content_to_message_param_preserves_reasoning_newlines():
+  thought_part_1 = types.Part.from_text(text="line 1\n")
+  thought_part_1.thought = True
+  thought_part_2 = types.Part.from_text(text="line 2")
+  thought_part_2.thought = True
+  content = types.Content(
+      role="assistant", parts=[thought_part_1, thought_part_2]
+  )
+
+  message = await _content_to_message_param(content)
+
+  assert message["reasoning_content"] == "line 1\nline 2"
+
+
 @pytest.mark.asyncio
 async def test_content_to_message_param_function_call():
   content = types.Content(