BerriAI/litellm · error · HTTPException

Failed to update policy override for tool '{data.tool_name}'

Error message

Failed to update policy override for tool '{data.tool_name}'

What it means

Error "Failed to update policy override for tool '{data.tool_name}'" thrown in BerriAI/litellm.

Source

Thrown at litellm/proxy/management_endpoints/tool_management_endpoints.py:648

                raise HTTPException(
                    status_code=404,
                    detail="Key or team not found for the given identifier",
                )
            is_blocking: Final = data.input_policy == "blocked"
            if is_blocking:
                ok = await add_tool_to_object_permission_blocked(
                    prisma_client=prisma_client,
                    object_permission_id=op_id,
                    tool_name=data.tool_name,
                )
            else:
                ok = await remove_tool_from_object_permission_blocked(
                    prisma_client=prisma_client,
                    object_permission_id=op_id,
                    tool_name=data.tool_name,
                )
            if not ok:
                raise HTTPException(
                    status_code=500,
                    detail=f"Failed to update policy override for tool '{data.tool_name}'",
                )
            registry = get_tool_policy_registry()
            if registry.is_initialized():
                await registry.sync_tool_policy_from_db(prisma_client)
            return ToolPolicyUpdateResponse(
                tool_name=data.tool_name,
                input_policy=data.input_policy,
                output_policy=data.output_policy,
                updated=True,
                team_id=data.team_id,
                key_hash=data.key_hash,
            )

        if data.input_policy is None and data.output_policy is None:
            raise HTTPException(
                status_code=400,

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Verify the tool name and override scope exist, check proxy logs, then retry.

When it happens

Trigger: Thrown at litellm/proxy/management_endpoints/tool_management_endpoints.py:648 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/673385cfcab00f1a. Report an issue: GitHub.