Merge pull request #21629 from Chesars/fix/pydantic-serialization-warnings

fix(types): remove StreamingChoices from ModelResponse, use ModelResponseStream

litellm/litellm_core_utils/streaming_handler.py

@@ -1231,7 +1231,7 @@ class CustomStreamWrapper:
                                     ],
                                 )
                                 _streaming_response = StreamingChoices(delta=_delta_obj)
-                                _model_response = ModelResponse(stream=True)
+                                _model_response = ModelResponseStream()
                                 _model_response.choices = [_streaming_response]
                                 response_obj = {"original_chunk": _model_response}
                             else:

litellm/llms/bedrock/chat/agentcore/transformation.py

@@ -26,7 +26,7 @@ from litellm.types.llms.bedrock_agentcore import (
     AgentCoreUsage,
 )
 from litellm.types.llms.openai import AllMessageValues
-from litellm.types.utils import Choices, Delta, Message, ModelResponse, StreamingChoices, Usage
+from litellm.types.utils import Choices, Delta, Message, ModelResponse, ModelResponseStream, StreamingChoices, Usage
 
 if TYPE_CHECKING:
     from litellm.litellm_core_utils.litellm_logging import Logging as _LiteLLMLoggingObj
@@ -481,7 +481,7 @@ class AmazonAgentCoreConfig(BaseConfig, BaseAWSLLM):
                             text = delta.get("text", "")
 
                             if text:
-                                chunk = ModelResponse(
+                                chunk = ModelResponseStream(
                                     id=f"chatcmpl-{uuid.uuid4()}",
                                     created=0,
                                     model=model,
@@ -499,7 +499,7 @@ class AmazonAgentCoreConfig(BaseConfig, BaseAWSLLM):
                         # Process metadata/usage
                         metadata = event_payload.get("metadata")
                         if metadata and "usage" in metadata:
-                            chunk = ModelResponse(
+                            chunk = ModelResponseStream(
                                 id=f"chatcmpl-{uuid.uuid4()}",
                                 created=0,
                                 model=model,
@@ -522,7 +522,7 @@ class AmazonAgentCoreConfig(BaseConfig, BaseAWSLLM):
 
                     # Process final message
                     if "message" in data_obj and isinstance(data_obj["message"], dict):
-                        chunk = ModelResponse(
+                        chunk = ModelResponseStream(
                             id=f"chatcmpl-{uuid.uuid4()}",
                             created=0,
                             model=model,
@@ -601,7 +601,7 @@ class AmazonAgentCoreConfig(BaseConfig, BaseAWSLLM):
         self,
         response: httpx.Response,
         model: str,
-    ) -> AsyncGenerator[ModelResponse, None]:
+    ) -> AsyncGenerator[ModelResponseStream, None]:
         """
         Internal async generator that parses SSE and yields ModelResponse chunks.
         """
@@ -636,7 +636,7 @@ class AmazonAgentCoreConfig(BaseConfig, BaseAWSLLM):
                             text = delta.get("text", "")
 
                             if text:
-                                chunk = ModelResponse(
+                                chunk = ModelResponseStream(
                                     id=f"chatcmpl-{uuid.uuid4()}",
                                     created=0,
                                     model=model,
@@ -654,7 +654,7 @@ class AmazonAgentCoreConfig(BaseConfig, BaseAWSLLM):
                         # Process metadata/usage
                         metadata = event_payload.get("metadata")
                         if metadata and "usage" in metadata:
-                            chunk = ModelResponse(
+                            chunk = ModelResponseStream(
                                 id=f"chatcmpl-{uuid.uuid4()}",
                                 created=0,
                                 model=model,
@@ -677,7 +677,7 @@ class AmazonAgentCoreConfig(BaseConfig, BaseAWSLLM):
 
                     # Process final message
                     if "message" in data_obj and isinstance(data_obj["message"], dict):
-                        chunk = ModelResponse(
+                        chunk = ModelResponseStream(
                             id=f"chatcmpl-{uuid.uuid4()}",
                             created=0,
                             model=model,

litellm/llms/bedrock/chat/invoke_handler.py

@@ -558,7 +558,7 @@ class BedrockLLM(BaseAWSLLM):
                             "INSIDE BEDROCK STREAMING TOOL CALLING CONDITION BLOCK"
                         )
                         # return an iterator
-                        streaming_model_response = ModelResponse(stream=True)
+                        streaming_model_response = ModelResponseStream()
                         streaming_model_response.choices[0].finish_reason = getattr(
                             model_response.choices[0], "finish_reason", "stop"
                         )
@@ -695,7 +695,7 @@ class BedrockLLM(BaseAWSLLM):
             )
 
         if stream and provider == "ai21":
-            streaming_model_response = ModelResponse(stream=True)
+            streaming_model_response = ModelResponseStream()
             streaming_model_response.choices[0].finish_reason = model_response.choices[  # type: ignore
                 0
             ].finish_reason

litellm/llms/bedrock/chat/invoke_transformations/amazon_qwen2_transformation.py

@@ -68,13 +68,8 @@ class AmazonQwen2Config(AmazonQwen3Config):
             # Set the content in the existing model_response structure
             if hasattr(model_response, 'choices') and len(model_response.choices) > 0:
                 choice = model_response.choices[0]
-                if hasattr(choice, 'message'):
-                    choice.message.content = generated_text
-                    choice.finish_reason = "stop"
-                else:
-                    # Handle streaming choices
-                    choice.delta.content = generated_text
-                    choice.finish_reason = "stop"
+                choice.message.content = generated_text
+                choice.finish_reason = "stop"
             
             # Set usage information if available in response
             if "usage" in response_data:

litellm/llms/bedrock/chat/invoke_transformations/amazon_qwen3_transformation.py

@@ -190,13 +190,8 @@ class AmazonQwen3Config(AmazonInvokeConfig, BaseConfig):
             # Set the content in the existing model_response structure
             if hasattr(model_response, 'choices') and len(model_response.choices) > 0:
                 choice = model_response.choices[0]
-                if hasattr(choice, 'message'):
-                    choice.message.content = generated_text
-                    choice.finish_reason = "stop"
-                else:
-                    # Handle streaming choices
-                    choice.delta.content = generated_text
-                    choice.finish_reason = "stop"
+                choice.message.content = generated_text
+                choice.finish_reason = "stop"
             
             # Set usage information if available in response
             if "usage" in response_data:

litellm/llms/codestral/completion/transformation.py

@@ -102,7 +102,7 @@ class CodestralTextCompletionConfig(OpenAITextCompletionConfig):
                 "finish_reason": finish_reason,
             }
 
-        original_chunk = litellm.ModelResponse(**chunk_data_dict, stream=True)
+        original_chunk = litellm.ModelResponseStream(**chunk_data_dict)
         _choices = chunk_data_dict.get("choices", []) or []
         if len(_choices) == 0:
             return {

litellm/llms/langgraph/chat/sse_iterator.py

@@ -11,7 +11,7 @@ from typing import TYPE_CHECKING, Optional
 import httpx
 
 from litellm._logging import verbose_logger
-from litellm.types.utils import Delta, ModelResponse, StreamingChoices
+from litellm.types.utils import Delta, ModelResponseStream, StreamingChoices
 
 if TYPE_CHECKING:
     pass
@@ -44,7 +44,7 @@ class LangGraphSSEStreamIterator:
         self.async_line_iterator = self.response.aiter_lines()
         return self
 
-    def _parse_sse_line(self, line: str) -> Optional[ModelResponse]:
+    def _parse_sse_line(self, line: str) -> Optional[ModelResponseStream]:
         """
         Parse a single SSE line and return a ModelResponse chunk if applicable.
 
@@ -71,7 +71,7 @@ class LangGraphSSEStreamIterator:
 
         return None
 
-    def _process_data(self, data) -> Optional[ModelResponse]:
+    def _process_data(self, data) -> Optional[ModelResponseStream]:
         """
         Process parsed data from SSE stream.
 
@@ -101,7 +101,7 @@ class LangGraphSSEStreamIterator:
 
         return None
 
-    def _process_messages_event(self, payload) -> Optional[ModelResponse]:
+    def _process_messages_event(self, payload) -> Optional[ModelResponseStream]:
         """
         Process a messages event from the stream.
 
@@ -128,7 +128,7 @@ class LangGraphSSEStreamIterator:
 
         return None
 
-    def _process_metadata_event(self, payload) -> Optional[ModelResponse]:
+    def _process_metadata_event(self, payload) -> Optional[ModelResponseStream]:
         """
         Process a metadata event, which may signal the end of the stream.
         """
@@ -139,9 +139,9 @@ class LangGraphSSEStreamIterator:
                 return self._create_final_chunk()
         return None
 
-    def _create_content_chunk(self, text: str) -> ModelResponse:
-        """Create a ModelResponse chunk with content."""
-        chunk = ModelResponse(
+    def _create_content_chunk(self, text: str) -> ModelResponseStream:
+        """Create a ModelResponseStream chunk with content."""
+        chunk = ModelResponseStream(
             id=f"chatcmpl-{uuid.uuid4()}",
             created=0,
             model=self.model,
@@ -158,9 +158,9 @@ class LangGraphSSEStreamIterator:
 
         return chunk
 
-    def _create_final_chunk(self) -> ModelResponse:
-        """Create a final ModelResponse chunk with finish_reason."""
-        chunk = ModelResponse(
+    def _create_final_chunk(self) -> ModelResponseStream:
+        """Create a final ModelResponseStream chunk with finish_reason."""
+        chunk = ModelResponseStream(
             id=f"chatcmpl-{uuid.uuid4()}",
             created=0,
             model=self.model,
@@ -177,7 +177,7 @@ class LangGraphSSEStreamIterator:
 
         return chunk
 
-    def __next__(self) -> ModelResponse:
+    def __next__(self) -> ModelResponseStream:
         """Sync iteration - parse SSE events and yield ModelResponse chunks."""
         try:
             if self.line_iterator is None:
@@ -205,7 +205,7 @@ class LangGraphSSEStreamIterator:
             verbose_logger.error(f"Error in LangGraph SSE stream: {str(e)}")
             raise StopIteration
 
-    async def __anext__(self) -> ModelResponse:
+    async def __anext__(self) -> ModelResponseStream:
         """Async iteration - parse SSE events and yield ModelResponse chunks."""
         try:
             if self.async_line_iterator is None:

litellm/llms/openai/chat/guardrail_translation/handler.py

@@ -542,16 +542,16 @@ class OpenAIChatCompletionsHandler(BaseTranslation):
                         if len(choice.message.tool_calls) > 0:
                             return True
         elif isinstance(response, ModelResponseStream):
-            for choice in response.choices:
-                if isinstance(choice, litellm.StreamingChoices):
+            for streaming_choice in response.choices:
+                if isinstance(streaming_choice, litellm.StreamingChoices):
                     # Check for text content
-                    if choice.delta.content and isinstance(choice.delta.content, str):
+                    if streaming_choice.delta.content and isinstance(streaming_choice.delta.content, str):
                         return True
                     # Check for tool calls
-                    if choice.delta.tool_calls and isinstance(
-                        choice.delta.tool_calls, list
+                    if streaming_choice.delta.tool_calls and isinstance(
+                        streaming_choice.delta.tool_calls, list
                     ):
-                        if len(choice.delta.tool_calls) > 0:
+                        if len(streaming_choice.delta.tool_calls) > 0:
                             return True
         return False
 

litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py

@@ -2100,7 +2100,7 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                     chat_completion_logprobs=chat_completion_logprobs,
                     image_response=image_response,
                 )
-                model_response.choices.append(choice)
+                model_response.choices.append(choice)  # type: ignore[arg-type]
             elif isinstance(model_response, ModelResponse):
                 choice = litellm.Choices(
                     finish_reason=VertexGeminiConfig._check_finish_reason(
@@ -2111,7 +2111,7 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                     logprobs=chat_completion_logprobs,
                     enhancements=None,
                 )
-                model_response.choices.append(choice)
+                model_response.choices.append(choice)  # type: ignore[arg-type]
 
         return (
             grounding_metadata,

litellm/proxy/guardrails/guardrail_hooks/presidio.py

@@ -61,7 +61,6 @@ from litellm.utils import (
     ImageResponse,
     ModelResponse,
     ModelResponseStream,
-    StreamingChoices,
 )
 
 
@@ -863,9 +862,7 @@ class _OPTIONAL_PresidioPIIMasking(CustomGuardrail):
         if self.output_parse_pii is False and litellm.output_parse_pii is False:
             return response
 
-        if isinstance(response, ModelResponse) and not isinstance(
-            response.choices[0], StreamingChoices
-        ):  # /chat/completions requests
+        if isinstance(response, ModelResponse):  # /chat/completions requests
             if isinstance(response.choices[0].message.content, str):
                 verbose_proxy_logger.debug(
                     f"self.pii_tokens: {self.pii_tokens}; initial response: {response.choices[0].message.content}"
@@ -888,7 +885,7 @@ class _OPTIONAL_PresidioPIIMasking(CustomGuardrail):
             return response
 
         # skip streaming here; handled in async_post_call_streaming_iterator_hook
-        if response.choices and isinstance(response.choices[0], StreamingChoices):
+        if isinstance(response, ModelResponseStream):
             return response
 
         presidio_config = self.get_presidio_settings_from_request_data(
@@ -896,10 +893,7 @@ class _OPTIONAL_PresidioPIIMasking(CustomGuardrail):
         )
 
         for choice in response.choices:
-            # Type narrowing: StreamingChoices doesn't have .message attribute
-            if not hasattr(choice, "message"):
-                continue
-            content = getattr(choice.message, "content", None)  # type: ignore
+            content = getattr(choice.message, "content", None)
             if content is None:
                 continue
             if isinstance(content, str):

litellm/types/utils.py

@@ -1651,6 +1651,7 @@ class StreamingChatCompletionChunk(OpenAIChatCompletionChunk):
         super().__init__(**kwargs)
 
 
+
 class ModelResponseBase(OpenAIObject):
     id: str
     """A unique identifier for the completion."""
@@ -1759,7 +1760,7 @@ class ModelResponseStream(ModelResponseBase):
 
 
 class ModelResponse(ModelResponseBase):
-    choices: List[Union[Choices, StreamingChoices]]
+    choices: List[Choices]
     """The list of completion choices the model generated for the input prompt."""
 
     def __init__(  # noqa: PLR0915
@@ -1778,44 +1779,27 @@ class ModelResponse(ModelResponseBase):
         _response_headers=None,
         **params,
     ) -> None:
-        if stream is not None and stream is True:
-            object = "chat.completion.chunk"
-            if choices is not None and isinstance(choices, list):
-                new_choices = []
-                for choice in choices:
-                    _new_choice = None
-                    if isinstance(choice, StreamingChoices):
-                        _new_choice = choice
-                    elif isinstance(choice, dict):
-                        _new_choice = StreamingChoices(**choice)
-                    elif isinstance(choice, BaseModel):
-                        _new_choice = StreamingChoices(**choice.model_dump())
-                    new_choices.append(_new_choice)
-                choices = new_choices
-            else:
-                choices = [StreamingChoices()]
+        object = "chat.completion"
+        if choices is not None and isinstance(choices, list):
+            new_choices = []
+            for choice in choices:
+                if isinstance(choice, Choices):
+                    _new_choice = choice  # type: ignore
+                elif isinstance(choice, dict):
+                    _new_choice = Choices(**choice)  # type: ignore
+                elif isinstance(choice, BaseModel):
+                    dump = (
+                        choice.model_dump()
+                        if hasattr(choice, "model_dump")
+                        else choice.dict()
+                    )
+                    _new_choice = Choices(**dump)  # type: ignore
+                else:
+                    _new_choice = choice
+                new_choices.append(_new_choice)
+            choices = new_choices
         else:
-            object = "chat.completion"
-            if choices is not None and isinstance(choices, list):
-                new_choices = []
-                for choice in choices:
-                    if isinstance(choice, Choices):
-                        _new_choice = choice  # type: ignore
-                    elif isinstance(choice, dict):
-                        _new_choice = Choices(**choice)  # type: ignore
-                    elif isinstance(choice, BaseModel):
-                        dump = (
-                            choice.model_dump()
-                            if hasattr(choice, "model_dump")
-                            else choice.dict()
-                        )
-                        _new_choice = Choices(**dump)  # type: ignore
-                    else:
-                        _new_choice = choice
-                    new_choices.append(_new_choice)
-                choices = new_choices
-            else:
-                choices = [Choices()]
+            choices = [Choices()]
         if id is None:
             id = _generate_id()
         else:

litellm/utils.py

@@ -4963,9 +4963,7 @@ def get_response_string(response_obj: Union[ModelResponse, ModelResponseStream])
             return delta if isinstance(delta, str) else ""
 
     # Handle standard ModelResponse and ModelResponseStream
-    _choices: Union[List[Union[Choices, StreamingChoices]], List[StreamingChoices]] = (
-        response_obj.choices
-    )
+    _choices: Union[List[Choices], List[StreamingChoices]] = response_obj.choices
 
     # Use list accumulation to avoid O(n^2) string concatenation across choices
     response_parts: List[str] = []
@@ -7384,9 +7382,9 @@ def _get_base_model_from_metadata(model_call_details=None):
 class ModelResponseIterator:
     def __init__(self, model_response: ModelResponse, convert_to_delta: bool = False):
         if convert_to_delta is True:
-            self.model_response = ModelResponse(stream=True)
-            _delta = self.model_response.choices[0].delta  # type: ignore
-            _delta.content = model_response.choices[0].message.content  # type: ignore
+            _stream_response = ModelResponseStream()
+            _stream_response.choices[0].delta.content = model_response.choices[0].message.content  # type: ignore
+            self.model_response: Union[ModelResponse, ModelResponseStream] = _stream_response
         else:
             self.model_response = model_response
         self.is_done = False

tests/litellm/test_stream_chunk_builder_images.py

@@ -72,7 +72,7 @@ def test_stream_chunk_builder_preserves_images():
 
     chunks = []
     for chunk in init_chunks:
-        chunks.append(litellm.ModelResponse(**chunk, stream=True))
+        chunks.append(litellm.ModelResponseStream(**chunk))
 
     response = stream_chunk_builder(chunks=chunks)
 
@@ -163,7 +163,7 @@ def test_stream_chunk_builder_preserves_multiple_images():
 
     chunks = []
     for chunk in init_chunks:
-        chunks.append(litellm.ModelResponse(**chunk, stream=True))
+        chunks.append(litellm.ModelResponseStream(**chunk))
 
     response = stream_chunk_builder(chunks=chunks)
 
@@ -230,7 +230,7 @@ def test_stream_chunk_builder_no_images():
 
     chunks = []
     for chunk in init_chunks:
-        chunks.append(litellm.ModelResponse(**chunk, stream=True))
+        chunks.append(litellm.ModelResponseStream(**chunk))
 
     response = stream_chunk_builder(chunks=chunks)
 

tests/local_testing/test_stream_chunk_builder.py

@@ -542,7 +542,7 @@ def test_stream_chunk_builder_multiple_tool_calls():
 
     chunks = []
     for chunk in init_chunks:
-        chunks.append(litellm.ModelResponse(**chunk, stream=True))
+        chunks.append(litellm.ModelResponseStream(**chunk))
     response = stream_chunk_builder(chunks=chunks)
 
     print(f"Returned response: {response}")
@@ -616,7 +616,7 @@ def test_stream_chunk_builder_openai_prompt_caching():
     chunks: List[litellm.ModelResponse] = []
     usage_obj = None
     for chunk in chat_completion:
-        chunks.append(litellm.ModelResponse(**chunk.model_dump(), stream=True))
+        chunks.append(litellm.ModelResponseStream(**chunk.model_dump()))
 
     print(f"chunks: {chunks}")
 
@@ -661,7 +661,7 @@ def test_stream_chunk_builder_openai_audio_output_usage():
 
     chunks = []
     for chunk in completion:
-        chunks.append(litellm.ModelResponse(**chunk.model_dump(), stream=True))
+        chunks.append(litellm.ModelResponseStream(**chunk.model_dump()))
 
     usage_obj: Optional[litellm.Usage] = None
 

tests/local_testing/test_streaming.py

@@ -393,7 +393,7 @@ def test_completion_azure_stream_content_filter_no_delta():
 
         chunk_list = []
         for chunk in chunks:
-            new_chunk = litellm.ModelResponse(stream=True, id=chunk["id"])
+            new_chunk = litellm.ModelResponseStream(id=chunk["id"])
             if "choices" in chunk and isinstance(chunk["choices"], list):
                 new_choices = []
                 for choice in chunk["choices"]:
@@ -3026,7 +3026,7 @@ def test_unit_test_custom_stream_wrapper():
             {"index": 0, "delta": {"content": "How are you?"}, "finish_reason": "stop"}
         ],
     }
-    chunk = litellm.ModelResponse(**chunk, stream=True)
+    chunk = litellm.ModelResponseStream(**chunk)
 
     completion_stream = ModelResponseIterator(model_response=chunk)
 
@@ -3223,7 +3223,7 @@ def test_unit_test_custom_stream_wrapper_openai():
         "system_fingerprint": None,
         "usage": None,
     }
-    chunk = litellm.ModelResponse(**chunk, stream=True)
+    chunk = litellm.ModelResponseStream(**chunk)
 
     completion_stream = ModelResponseIterator(model_response=chunk)
 
@@ -3457,7 +3457,7 @@ def test_aamazing_unit_test_custom_stream_wrapper_n():
 
     chunk_list = []
     for chunk in chunks:
-        new_chunk = litellm.ModelResponse(stream=True, id=chunk["id"])
+        new_chunk = litellm.ModelResponseStream(id=chunk["id"])
         if "choices" in chunk and isinstance(chunk["choices"], list):
             print("INSIDE CHUNK CHOICES!")
             new_choices = []
@@ -3541,7 +3541,7 @@ def test_unit_test_custom_stream_wrapper_function_call():
         "system_fingerprint": "fp_44709d6fcb",
         "choices": [{"index": 0, "delta": delta, "finish_reason": "stop"}],
     }
-    chunk = litellm.ModelResponse(**chunk, stream=True)
+    chunk = litellm.ModelResponseStream(**chunk)
 
     completion_stream = ModelResponseIterator(model_response=chunk)
 
@@ -3651,7 +3651,7 @@ def test_unit_test_perplexity_citations_chunk():
             }
         ],
     }
-    chunk = litellm.ModelResponse(**chunk, stream=True)
+    chunk = litellm.ModelResponseStream(**chunk)
 
     completion_stream = ModelResponseIterator(model_response=chunk)
 

tests/test_litellm/test_model_response_normalization.py

@@ -2,7 +2,14 @@ import warnings
 
 import pytest
 
-from litellm.types.utils import Choices, Message, ModelResponse
+from litellm.types.utils import (
+    Choices,
+    Delta,
+    Message,
+    ModelResponse,
+    ModelResponseStream,
+    StreamingChoices,
+)
 
 
 def test_modelresponse_normalizes_openai_base_models() -> None:
@@ -59,3 +66,63 @@ def test_modelresponse_serialization_avoids_pydantic_warnings() -> None:
         or "Pydantic serializer warnings" in str(w.message)
         for w in captured
     )
+
+
+def test_modelresponse_model_dump_json_no_pydantic_warnings() -> None:
+    """model_dump_json() and model_dump() should not trigger any Pydantic
+    serialization warnings now that choices is List[Choices] (no Union)."""
+    response = ModelResponse(
+        model="test-model",
+        choices=[
+            Choices(
+                finish_reason="stop",
+                index=0,
+                message=Message(content="hello", role="assistant"),
+            )
+        ],
+    )
+
+    with warnings.catch_warnings(record=True) as captured:
+        warnings.simplefilter("always")
+        _ = response.model_dump_json()
+        _ = response.model_dump()
+        _ = response.model_dump(exclude_none=True)
+
+    pydantic_warnings = [
+        w
+        for w in captured
+        if "PydanticSerializationUnexpectedValue" in str(w.message)
+        or "Pydantic serializer warnings" in str(w.message)
+    ]
+    assert pydantic_warnings == [], (
+        f"Unexpected Pydantic serialization warnings: {pydantic_warnings}"
+    )
+
+
+def test_streaming_modelresponsestream_no_pydantic_warnings() -> None:
+    """Streaming responses use ModelResponseStream with List[StreamingChoices]
+    and should serialize without warnings."""
+    response = ModelResponseStream(
+        choices=[
+            StreamingChoices(
+                finish_reason="stop",
+                index=0,
+                delta=Delta(content="hello", role="assistant"),
+            )
+        ],
+    )
+
+    with warnings.catch_warnings(record=True) as captured:
+        warnings.simplefilter("always")
+        _ = response.model_dump_json()
+        _ = response.model_dump()
+
+    pydantic_warnings = [
+        w
+        for w in captured
+        if "PydanticSerializationUnexpectedValue" in str(w.message)
+        or "Pydantic serializer warnings" in str(w.message)
+    ]
+    assert pydantic_warnings == [], (
+        f"Unexpected Pydantic serialization warnings: {pydantic_warnings}"
+    )