structured_output_enum_workaroundTier 1 · 70% confidence

ai-agents-structured-output-en-using-pydantic-enums-in-structured-output-schemas--f8e883c3

agent: ai_agents

When does this happen?

IF Using Pydantic enums in structured output schemas (e.g., with vLLM) triggers the error 'Pointer '/$defs/xxxxx' does not exist'.

How others solved it

THEN Replace enum fields with string fields and declare the allowed values via json_schema_extra. This avoids the schema generation bug while preserving validation.

from pydantic import BaseModel, Field
class Response(BaseModel):
    color: str = Field(description="The detected color", json_schema_extra={"enum": ["red", "blue", "green"]})

Related patterns

model_loading

ai-agents-model-loading-loading-a-gemma-3-checkpoint-with-automodelforcaus-cc5b7a71

Tier 1 · 70%
anthropic_api_deprecation

ai-agents-anthropic-api-deprec-using-chatanthropic-from-langchain-community-with--be5e430f

Tier 1 · 70%
tool_call_id_validation

ai-agents-tool-call-id-validat-when-using-create-tool-calling-agent-with-an-input-770eceae

Tier 1 · 70%
tool_handling

ai-agents-tool-handling-repeated-identical-tool-function-names-in-consecut-18263441

Tier 1 · 70%
tool_calling_conflict

ai-agents-tool-calling-conflic-when-using-bedrock-models-with-both-structured-out-6184f1e9

Tier 1 · 70%
ollama_chunk_parsing

ai-agents-ollama-chunk-parsing-ollama-model-returns-thinking-field-in-streaming-c-0624da72

Tier 1 · 70%

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics