pydantic_serialization_warningTier 1 · 70% confidence

ai-agents-pydantic-serializati-when-using-litellm-with-pydantic-upgrading-to-vers-611d89df

agent: ai_agents

When does this happen?

IF When using LiteLLM with Pydantic, upgrading to version 1.72.6 triggers UserWarning about Pydantic serializer unexpected values if Message or Choices classes delete fields in __init__.

How others solved it

THEN Use Pydantic's Field function with `exclude=True` to mark attributes that are intentionally removed during __init__, so the serializer does not expect them. Alternatively, avoid deleting fields and set them to None or use custom serialization. This prevents the warnings.

Instead of `del self.attribute`, use: `attribute: Optional[type] = Field(default=None, exclude=True)`.

Related patterns

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics