What causes "OpenAI selected but no valid OpenAI auth is configured." in nexu-io/open-design?

Set OPENAI_API_KEY and OPENAI_AUTH_STATUS=ok together when using API-key auth.

nexu-io/open-design · error · RuntimeError

OpenAI selected but no valid OpenAI auth is configured.

Error message

OpenAI selected but no valid OpenAI auth is configured.

What it means

Raised in resolve_runtime when provider_name is 'openai' but either OPENAI_API_KEY is empty or OPENAI_AUTH_STATUS != 'ok'. Unlike gemini, OpenAI requires BOTH a token and an explicit auth-status handshake (env.AUTH_STATUS_OK) because the runtime also supports ChatGPT-session auth, not just API keys.

Source

Thrown at design-templates/last30days/scripts/lib/providers.py:299

            ), None

    planner_model, rerank_model = _resolve_model_pins(config, depth, provider_name)

    if provider_name == "gemini":
        if not google_key:
            raise RuntimeError("Gemini selected but no Google API key is configured.")
        runtime = schema.ProviderRuntime(
            reasoning_provider="gemini",
            planner_model=planner_model,
            rerank_model=rerank_model,

            x_search_backend=_resolve_x_backend(config),
        )
        return runtime, GeminiClient(google_key)

    if provider_name == "openai":
        if not openai_token or config.get("OPENAI_AUTH_STATUS") != env.AUTH_STATUS_OK:
            raise RuntimeError("OpenAI selected but no valid OpenAI auth is configured.")
        runtime = schema.ProviderRuntime(
            reasoning_provider="openai",
            planner_model=planner_model,
            rerank_model=rerank_model,

            x_search_backend=_resolve_x_backend(config),
        )
        return runtime, OpenAIClient(
            openai_token,
            config.get("OPENAI_AUTH_SOURCE") or env.AUTH_SOURCE_API_KEY,
            config.get("OPENAI_CHATGPT_ACCOUNT_ID"),
        )

    if provider_name == "xai":
        if not xai_key:
            raise RuntimeError("xAI selected but XAI_API_KEY is not configured.")
        runtime = schema.ProviderRuntime(
            reasoning_provider="xai",

View on GitHub (pinned to 5be4028344)

Solutions

Set OPENAI_API_KEY and OPENAI_AUTH_STATUS=ok together when using API-key auth.
Re-run the OpenAI login/handshake step so it stamps OPENAI_AUTH_STATUS=ok into config.
If you do not have valid OpenAI auth, switch LAST30DAYS_REASONING_PROVIDER to gemini/xai/openrouter/auto.

Example fix

# before
OPENAI_API_KEY=sk-...
# OPENAI_AUTH_STATUS missing

# after
OPENAI_API_KEY=sk-...
OPENAI_AUTH_STATUS=ok
OPENAI_AUTH_SOURCE=api_key

Defensive patterns

Strategy: validation

Validate before calling

from lib import env

def ensure_openai_auth(config):
    token = config.get("OPENAI_API_KEY")
    status = config.get("OPENAI_AUTH_STATUS")
    if not token or status != env.AUTH_STATUS_OK:
        raise RuntimeError(
            "OpenAI provider requires OPENAI_API_KEY and OPENAI_AUTH_STATUS=ok."
        )
    return token

Type guard

null

Try / catch

null

Prevention

When using API-key auth, always set OPENAI_API_KEY together with OPENAI_AUTH_STATUS=ok and OPENAI_AUTH_SOURCE=api_key.
Re-run the OpenAI auth handshake whenever the token is refreshed so the status field stays 'ok'.
Use 'auto' provider selection so an incomplete OpenAI auth falls through to another provider.

When it happens

Trigger: LAST30DAYS_REASONING_PROVIDER=openai with OPENAI_API_KEY set but OPENAI_AUTH_STATUS unset or set to a non-'ok' value. Also reached via auto-resolution when a key exists but the auth handshake failed.

Common situations: Setting OPENAI_API_KEY directly without also setting OPENAI_AUTH_STATUS=ok. Auth token expired (ChatGPT session refresh failed) so status flipped to a non-ok value. Auto-resolution picked openai because the key was present but the status check was skipped.

Related errors

AI-assisted analysis of nexu-io/open-design@5be4028344 (2026-08-12). Data as JSON: /api/errors/6265f3e7624d08e8. Report an issue: GitHub.