What causes "Unsupported reasoning provider: {provider_name}" in nexu-io/open-design?

Set LAST30DAYS_REASONING_PROVIDER to one of gemini, openai, xai, openrouter, or auto.

nexu-io/open-design · error · RuntimeError

Unsupported reasoning provider: {provider_name}

Error message

Unsupported reasoning provider: {provider_name}

What it means

Raised in mock_runtime after normalizing 'auto' to 'gemini'. The provider name is checked against _MODEL_DEFAULTS, whose keys are exactly gemini, openai, xai, openrouter. Any other value (including typos or partially-supported providers) aborts mock mode before model pins are resolved.

Source

Thrown at design-templates/last30days/scripts/lib/providers.py:247

        default_rerank = GEMINI_PRO

    planner_model = config.get("LAST30DAYS_PLANNER_MODEL") or default_planner
    rerank_model = config.get("LAST30DAYS_RERANK_MODEL") or default_rerank

    if provider_name == "gemini":
        _require_gemini_31_preview(planner_model, role="planner")
        _require_gemini_31_preview(rerank_model, role="rerank")

    return planner_model, rerank_model


def mock_runtime(config: dict[str, Any], depth: str) -> schema.ProviderRuntime:
    """Resolve model pins for mock mode without requiring live credentials."""
    provider_name = (config.get("LAST30DAYS_REASONING_PROVIDER") or "gemini").lower()
    if provider_name == "auto":
        provider_name = "gemini"
    if provider_name not in _MODEL_DEFAULTS:
        raise RuntimeError(f"Unsupported reasoning provider: {provider_name}")

    planner_model, rerank_model = _resolve_model_pins(config, depth, provider_name)
    return schema.ProviderRuntime(
        reasoning_provider=provider_name,
        planner_model=planner_model,
        rerank_model=rerank_model,

        x_search_backend=_resolve_x_backend(config),
    )


def resolve_runtime(config: dict[str, Any], depth: str) -> tuple[schema.ProviderRuntime, ReasoningClient | None]:
    """Resolve the reasoning provider and pinned models."""
    provider_name = (config.get("LAST30DAYS_REASONING_PROVIDER") or "auto").lower()
    google_key = config.get("GOOGLE_API_KEY") or config.get("GEMINI_API_KEY") or config.get("GOOGLE_GENAI_API_KEY")
    openai_token = config.get("OPENAI_API_KEY")
    xai_key = config.get("XAI_API_KEY")

View on GitHub (pinned to 5be4028344)

Solutions

Set LAST30DAYS_REASONING_PROVIDER to one of gemini, openai, xai, openrouter, or auto.
Leave it unset to default to 'gemini' in mock mode.
If you need a new provider in mock mode, add its (planner, rerank) defaults to _MODEL_DEFAULTS in providers.py.

Example fix

# before
LAST30DAYS_REASONING_PROVIDER=anthropic

# after
LAST30DAYS_REASONING_PROVIDER=gemini

Defensive patterns

Strategy: validation

Validate before calling

SUPPORTED_PROVIDERS = {"gemini", "openai", "xai", "openrouter", "auto"}

def validate_mock_provider(config):
    p = (config.get("LAST30DAYS_REASONING_PROVIDER") or "gemini").lower()
    if p not in SUPPORTED_PROVIDERS:
        raise ValueError(f"Unsupported provider for mock mode: {p!r}")
    return p

Type guard

null

Try / catch

null

Prevention

Treat the _MODEL_DEFAULTS keys as the canonical provider allow-list and validate against it in one place.
Default LAST30DAYS_REASONING_PROVIDER to 'auto' or 'gemini' rather than leaving a chance of an unknown pin.
Surface a friendly config error at load time instead of letting mock_runtime raise mid-run.

When it happens

Trigger: Setting LAST30DAYS_REASONING_PROVIDER to a string outside {gemini, openai, xai, openrouter, auto} and running in mock mode (no live credentials).

Common situations: Trying to mock with a provider like 'anthropic' or 'mistral' that the runtime does not pin models for. A trailing space or uppercase variant ('OpenAI') after .lower() that still is not in the map (lower handles case, not unknown names).

Related errors

AI-assisted analysis of nexu-io/open-design@5be4028344 (2026-08-12). Data as JSON: /api/errors/a0b2a43db622690d. Report an issue: GitHub.