BerriAI/litellm · error · ValueError

Pangea guardrail name is required

Error message

Pangea guardrail name is required

What it means

Error "Pangea guardrail name is required" thrown in BerriAI/litellm.

Source

Thrown at litellm/proxy/guardrails/guardrail_hooks/pangea/__init__.py:16

from typing import TYPE_CHECKING, Final

from litellm.types.guardrails import SupportedGuardrailIntegrations

from .pangea import PangeaHandler

if TYPE_CHECKING:
    from litellm.types.guardrails import Guardrail, LitellmParams


def initialize_guardrail(litellm_params: "LitellmParams", guardrail: "Guardrail"):
    import litellm

    guardrail_name: Final = guardrail.get("guardrail_name")
    if not guardrail_name:
        raise ValueError("Pangea guardrail name is required")

    _pangea_callback: Final = PangeaHandler(
        guardrail_name=guardrail_name,
        pangea_input_recipe=litellm_params.pangea_input_recipe,
        pangea_output_recipe=litellm_params.pangea_output_recipe,
        api_base=litellm_params.api_base,
        api_key=litellm_params.api_key,
        event_hook=litellm_params.mode,
        default_on=litellm_params.default_on,
    )
    litellm.logging_callback_manager.add_litellm_callback(_pangea_callback)

    return _pangea_callback


guardrail_initializer_registry: Final = {
    SupportedGuardrailIntegrations.PANGEA.value: initialize_guardrail,
}

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Set guardrail_name in the pangea guardrail configuration.
2. Restart the proxy after adding a non-empty guardrail name.

When it happens

Trigger: Thrown at litellm/proxy/guardrails/guardrail_hooks/pangea/__init__.py:16 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/9f803e78a7dda8c0. Report an issue: GitHub.