BerriAI/litellm · error · ValueError

api_base is required for PydanticAIProviderConfig

Error message

api_base is required for PydanticAIProviderConfig

What it means

PydanticAIProviderConfig.handle_non_streaming raises ValueError when api_base is None. Pydantic AI agents are reached over plain HTTP; there is no model-to-endpoint derivation, so the agent URL must be supplied.

Source

Thrown at litellm/a2a_protocol/providers/pydantic_ai_agents/config.py:29

class PydanticAIProviderConfig(BaseA2AProviderConfig):
    """
    Provider configuration for Pydantic AI agents.

    Pydantic AI agents follow A2A protocol but don't support streaming natively.
    This config provides fake streaming by converting non-streaming responses into streaming chunks.
    """

    async def handle_non_streaming(
        self,
        request_id: str,
        params: dict[str, Any],
        api_base: str | None = None,
        **kwargs: Any,
    ) -> dict[str, Any]:
        """Handle non-streaming request to Pydantic AI agent."""
        if api_base is None:
            raise ValueError("api_base is required for PydanticAIProviderConfig")
        return await PydanticAIHandler.handle_non_streaming(
            request_id=request_id,
            params=params,
            api_base=api_base,
            timeout=kwargs.get("timeout", 60.0),
            agent_extra_headers=kwargs.get("agent_extra_headers"),
        )

    async def handle_streaming(
        self,
        request_id: str,
        params: dict[str, Any],
        api_base: str | None = None,
        **kwargs,
    ) -> AsyncIterator[dict[str, Any]]:
        """Handle streaming request with fake streaming."""
        if not api_base:
            raise ValueError("api_base is required for Pydantic AI agents")

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Pass api_base (the Pydantic AI agent server URL) to the handler
2. In LiteLLM proxy config, set api_base on the pydantic-ai agent deployment

Example fix

# before
resp = await config.handle_non_streaming(request_id=rid, params=params)
# after
resp = await config.handle_non_streaming(request_id=rid, params=params, api_base="http://localhost:8000")

from urllib.parse import urlparse
if not api_base or not urlparse(api_base).scheme:
    raise ValueError("pydantic-ai agent requires a valid api_base URL")

When it happens

Trigger: Calling the pydantic_ai_agents config handler for a non-streaming request with api_base=None in kwargs.

Common situations: Model added in the proxy without `api_base`; assuming the handler reads the base URL from litellm_params like AgentCore does.

Related errors

• api_base is required for Pydantic AI agents
• api_base is required for Pydantic AI agents
• request is required
• Either a2a_client or api_base is required for standard A2A f
• litellm_params is required for BedrockAgentCoreA2AConfig (mu

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/25232ca07514169e. Report an issue: GitHub.