BerriAI/litellm · error · HTTPException

Error in Pangea Guardrail

Error message

Error in Pangea Guardrail

What it means

Error "Error in Pangea Guardrail" thrown in BerriAI/litellm.

Source

Thrown at litellm/proxy/guardrails/guardrail_hooks/pangea/pangea.py:210

        self,
        user_api_key_dict: UserAPIKeyAuth,
        cache: DualCache,
        data: dict,
        call_type: str,
    ):
        event_type: Final = GuardrailEventHooks.pre_call
        if self.should_run_guardrail(data=data, event_type=event_type) is not True:
            verbose_proxy_logger.debug(
                "Pangea Guardrail (async_pre_call_hook): Guardrail is disabled %s.", self.guardrail_name
            )
            return data

        try:
            return await self._async_pre_call_hook(user_api_key_dict, cache, data, call_type)
        except HTTPException:
            raise
        except Exception as e:
            raise HTTPException(
                status_code=500,
                detail={
                    "error": "Error in Pangea Guardrail",
                    "guardrail_name": self.guardrail_name,
                    "exceptions": str(e),
                },
            ) from e

    async def _async_post_call_success_hook(
        self,
        data: dict,
        user_api_key_dict: UserAPIKeyAuth,
        # This union isn't actually correct -- it can get other response types depending on the API called
        response: LLMResponseTypes,
    ):
        if isinstance(response, TextCompletionResponse):
            # Assume the earlier call type as well
            input_messages = _TextCompletionRequest(data).get_messages()

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Check the proxy logs for the underlying Pangea API error.
2. Verify PANGEA_API_KEY and the Pangea service configuration are correct.
3. Confirm network connectivity to the Pangea API endpoint.

When it happens

Trigger: Thrown at litellm/proxy/guardrails/guardrail_hooks/pangea/pangea.py:210 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/285b024b4a7a9cff. Report an issue: GitHub.