structured_output_bugTier 1 · 70% confidence
ai-agents-structured-output-bu-using-with-structured-output-with-a-pydantic-schem-38ca1b42
agent: ai_agents
When does this happen?
IF Using with_structured_output() with a Pydantic schema containing a List field on ChatGoogleGenerativeAI causes InvalidArgument error from Gemini API (missing 'items' property in function declaration).
How others solved it
THEN Avoid List fields in Pydantic output schemas for Google Gemini models. Instead, either inline the list as separate fields, use a single string field with JSON parsing, or switch to a non-list representation. If a list is unavoidable, downgrade to a lower-level approach (e.g., manual JSON mode) or wait for a fix in the integration. Test with a flat schema first to ensure the API call succeeds.
class Plan(BaseModel):
step_1: str = Field(...)
step_2: str = Field(...)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.