BerriAI/litellm · error · ValueError

prompt must not be blank

Error message

prompt must not be blank

What it means

Pydantic field validator on the 'prompt' field of the routing-test request model: it fires when prompt is empty/whitespace-only after parsing. The request is rejected before any router logic runs because a routing test needs a non-blank prompt to classify.

Source

Thrown at litellm/types/management_endpoints/auto_router_endpoints.py:51

    )
    default_model: str | None = Field(
        default=None,
        description="Model to route to when no tier resolves, i.e. complexity_router_default_model",
    )
    router_name: str = Field(
        default=DEFAULT_ROUTING_TEST_ROUTER_NAME,
        description="Name reported as the router in the routing decision. Display only",
    )
    team_id: str | None = Field(
        default=None,
        description="Team the router is being created for. Required for a team admin, who may only test their own team's routers",
    )

    @field_validator("prompt")
    @classmethod
    def _require_non_blank_prompt(cls, value: str) -> str:
        if not value.strip():
            raise ValueError("prompt must not be blank")
        return value


class AutoRouterRoutingTestResponse(BaseModel):
    """Where one prompt would have been routed, and why."""

    routed_model: str = Field(description="The model group the router picked")
    routed_model_configured: bool = Field(
        description="Whether routed_model is a model group this proxy actually serves",
    )
    routing_decision: StandardLoggingRoutingDecision = Field(
        description="The decision record this request would have written to its log row",
    )


class AutoRouterCacheBucket(BaseModel):
    """One prompt-caching bucket of turns, with how often those turns hit the cache."""

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Provide a non-blank prompt string for the auto-router request.
2. Strip whitespace and reject empty prompts client-side.

When it happens

Trigger: Thrown at litellm/types/management_endpoints/auto_router_endpoints.py:51 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/836687db7059a550. Report an issue: GitHub.