BerriAI/litellm · error · ValueError

adaptive=True tier pools must be non-empty; empty tiers: {em

Error message

adaptive=True tier pools must be non-empty; empty tiers: {empty}

What it means

Config validator on ComplexityRouterConfig: adaptive mode requires all tier pools to be populated, but some tiers have empty model lists (named in the message) alongside non-empty ones; either fill or remove them.

Source

Thrown at litellm/router_strategy/complexity_router/config.py:645

            return None
        return [stripped for keyword in value if (stripped := keyword.strip())]

    @model_validator(mode="after")
    def _validate_llm_classifier_config(self) -> "ComplexityRouterConfig":
        if self.classifier_type == "llm" and self.classifier_llm_config is None:
            raise ValueError("classifier_llm_config is required when classifier_type is 'llm'")
        return self

    @model_validator(mode="after")
    def _validate_adaptive_pools(self) -> "ComplexityRouterConfig":
        if not self.adaptive:
            return self
        normalized = {tier: (models if isinstance(models, list) else [models]) for tier, models in self.tiers.items()}
        if not any(normalized.values()):
            raise ValueError("adaptive=True requires at least one non-empty tier pool")
        empty: Final = [tier for tier, models in normalized.items() if not models]
        if empty:
            raise ValueError(f"adaptive=True tier pools must be non-empty; empty tiers: {empty}")
        self.tiers = normalized
        return self

    @model_validator(mode="after")
    def _validate_semantic_matching(self) -> "ComplexityRouterConfig":
        if not self.semantic_keyword_matching:
            return self
        if not self.embedding_model:
            raise ValueError("embedding_model is required when semantic_keyword_matching is enabled")
        if not self.keyword_tier_rules:
            raise ValueError("keyword_tier_rules must be non-empty when semantic_keyword_matching is enabled")
        return self

    @model_validator(mode="after")
    def _validate_tier_labels(self) -> "ComplexityRouterConfig":
        if not self.tier_labels:
            return self
        blank: Final = tuple(sorted(tier.value for tier, label in self.tier_labels.items() if not label.strip()))

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Populate the empty tier pools with models, or disable adaptive.

When it happens

Trigger: Thrown at litellm/router_strategy/complexity_router/config.py:645 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/85612753bd1eab73. Report an issue: GitHub.