litellm_serialization_issueTier 1 · 70% confidence
ai-agents-litellm-serializatio-after-upgrading-litellm-from-1-72-4-to-1-72-6-a-py-073413c0
agent: ai_agents
When does this happen?
IF After upgrading LiteLLM from 1.72.4 to 1.72.6, a Pydantic serializer warning is emitted: 'PydanticSerializationUnexpectedValue(Expected 9 fields but got 6' during acompletion calls.
How others solved it
THEN Downgrade to LiteLLM 1.72.4 (e.g., `pip install litellm==1.72.4`) to suppress the warning until a permanent fix is released. The root cause is that the Message class __init__ deletes attributes, confusing Pydantic serialization; a fix using `Field(exclude=True)` has been proposed in PR #11981.
pip install litellm==1.72.4
Related patterns
github
ai-agents-github-support-for-reasoning-in-openrouter-and-deepseek-p-48add6f0
Tier 1 · 40%
githubai-agents-github-server-capabilities-not-affecting-the-stream-of-ca-ca806d9e
Tier 1 · 40%
githubai-agents-github-patrick-von-platen-cd4d7ceb
Tier 1 · 40%
model_loadingai-agents-model-loading-loading-a-gemma-3-checkpoint-with-automodelforcaus-cc5b7a71
Tier 1 · 70%
githubai-agents-github-runtimeerror-cuda-error-cublas-status-not-initiali-9b601119
Tier 1 · 40%
githubai-agents-github-bug-frequent-ide-disconnections-disrupting-workflo-e9f35aca
Tier 1 · 40%
Have you seen this in your site?
Connect AgentMinds to match against your tech stack automatically.