test(test_streaming.py): add unit testing for custom stream wrapper

litellm/tests/test_streaming.py

@@ -2212,3 +2212,71 @@ async def test_acompletion_claude_3_function_call_with_streaming():
         # raise Exception("it worked!")
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
+
+
+class ModelResponseIterator:
+    def __init__(self, model_response):
+        self.model_response = model_response
+        self.is_done = False
+
+    # Sync iterator
+    def __iter__(self):
+        return self
+
+    def __next__(self):
+        if self.is_done:
+            raise StopIteration
+        self.is_done = True
+        return self.model_response
+
+    # Async iterator
+    def __aiter__(self):
+        return self
+
+    async def __anext__(self):
+        if self.is_done:
+            raise StopAsyncIteration
+        self.is_done = True
+        return self.model_response
+
+
+def test_unit_test_custom_stream_wrapper():
+    """
+    Test if last streaming chunk ends with '?', if the message repeats itself.
+    """
+    litellm.set_verbose = False
+    chunk = {
+        "id": "chatcmpl-123",
+        "object": "chat.completion.chunk",
+        "created": 1694268190,
+        "model": "gpt-3.5-turbo-0125",
+        "system_fingerprint": "fp_44709d6fcb",
+        "choices": [
+            {"index": 0, "delta": {"content": "How are you?"}, "finish_reason": "stop"}
+        ],
+    }
+    chunk = litellm.ModelResponse(**chunk, stream=True)
+
+    completion_stream = ModelResponseIterator(model_response=chunk)
+
+    response = litellm.CustomStreamWrapper(
+        completion_stream=completion_stream,
+        model="gpt-3.5-turbo",
+        custom_llm_provider="cached_response",
+        logging_obj=litellm.Logging(
+            model="gpt-3.5-turbo",
+            messages=[{"role": "user", "content": "Hey"}],
+            stream=True,
+            call_type="completion",
+            start_time=time.time(),
+            litellm_call_id="12345",
+            function_id="1245",
+        ),
+    )
+
+    freq = 0
+    for chunk in response:
+        if chunk.choices[0].delta.content is not None:
+            if "How are you?" in chunk.choices[0].delta.content:
+                freq += 1
+    assert freq == 1

litellm/utils.py

@@ -422,8 +422,11 @@ class StreamingChoices(OpenAIObject):
         else:
             self.finish_reason = None
         self.index = index
-        if delta:
-            self.delta = delta
+        if delta is not None:
+            if isinstance(delta, Delta):
+                self.delta = delta
+            if isinstance(delta, dict):
+                self.delta = Delta(**delta)
         else:
             self.delta = Delta()
         if enhancements is not None:
@@ -491,14 +494,25 @@ class ModelResponse(OpenAIObject):
     ):
         if stream is not None and stream == True:
             object = "chat.completion.chunk"
-            choices = [StreamingChoices()]
+            if choices is not None and isinstance(choices, list):
+                new_choices = []
+                for choice in choices:
+                    _new_choice = StreamingChoices(**choice)
+                    new_choices.append(_new_choice)
+                choices = new_choices
+            else:
+                choices = [StreamingChoices()]
         else:
             if model in litellm.open_ai_embedding_models:
                 object = "embedding"
             else:
                 object = "chat.completion"
-            if choices:
-                choices = [Choices(*choices)]
+            if choices is not None and isinstance(choices, list):
+                new_choices = []
+                for choice in choices:
+                    _new_choice = Choices(**choice)
+                    new_choices.append(_new_choice)
+                choices = new_choices
             else:
                 choices = [Choices()]
         if id is None: