BerriAI/litellm · error · ValueError

IBM Guardrail Detector failed: {len(filtered_detections)} vi

Error message

IBM Guardrail Detector failed: {len(filtered_detections)} violation(s) detected

What it means

Error "IBM Guardrail Detector failed: {len(filtered_detections)} violation(s) detected" thrown in BerriAI/litellm.

Source

Thrown at litellm/proxy/guardrails/guardrail_hooks/ibm_guardrails/ibm_detector.py:475

            else:
                # Call orchestrator for each content separately
                for content in contents_to_check:
                    orchestrator_result = await self._call_orchestrator(
                        content=content,
                        request_data=data,
                        event_type=GuardrailEventHooks.pre_call,
                    )

                    verbose_proxy_logger.debug(
                        "IBM Orchestrator async_pre_call_hook result: %s",
                        orchestrator_result,
                    )

                    filtered = self._filter_detections_by_threshold(orchestrator_result)
                    if filtered and self.block_on_detection:
                        error_message = self._create_error_message_orchestrator(orchestrator_result)
                        raise ValueError(error_message)

        # Add guardrail to applied guardrails header
        add_guardrail_to_applied_guardrails_header(request_data=data, guardrail_name=self.guardrail_name)

        return data

    async def async_moderation_hook(
        self,
        data: dict,
        user_api_key_dict: UserAPIKeyAuth,
        call_type: CallTypesLiteral,
    ):
        """
        Runs in parallel to LLM API call
        Runs on only Input

        This can NOT modify the input, only used to reject or accept a call before going to LLM API
        """

View on GitHub (pinned to 77b7c6c40c)

Solutions

  1. Review which filtered detections triggered the block and modify the request content accordingly.
  2. Adjust detector score thresholds so legitimate content is not flagged.

When it happens

Trigger: Thrown at litellm/proxy/guardrails/guardrail_hooks/ibm_guardrails/ibm_detector.py:475 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/89123cb1ee9c91bb. Report an issue: GitHub.