mvanhorn/last30days-skill · critical · RuntimeError

OpenAI selected but no valid OpenAI auth is configured.

Error message

OpenAI selected but no valid OpenAI auth is configured.

What it means

RuntimeError raised in resolve_runtime for provider 'openai' when either the OpenAI token is missing or the OPENAI_AUTH_STATUS config entry is not the AUTH_STATUS_OK sentinel. The double gate means a merely-present token is insufficient - auth must have been validated by the env/onboarding layer.

Source

Thrown at skills/last30days/scripts/lib/providers.py:278

            ), 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
        )

    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",
            planner_model=planner_model,
            rerank_model=rerank_model,

View on GitHub (pinned to c7460f6114)

Solutions

  1. Re-run the setup/auth flow so the OpenAI token is validated and OPENAI_AUTH_STATUS is set to OK
  2. Replace an expired OPENAI_API_KEY with a working one and re-validate
  3. Verify both the token variable and the auth-status variable are loaded into the config dict, not just the shell

Example fix

# before
OPENAI_API_KEY=sk-expired...
# OPENAI_AUTH_STATUS unset -> raise

# after
OPENAI_API_KEY=sk-valid...
OPENAI_AUTH_STATUS=ok  # written by validated onboarding
Defensive patterns

Strategy: validation

Validate before calling

def openai_ready(config: dict) -> bool:
    return bool(
        config.get("OPENAI_API_KEY")
        and config.get("OPENAI_AUTH_STATUS") == "ok"
    )

Type guard

def openai_auth_ok(config: dict) -> bool:
    # both gates from providers.py: token present AND status validated
    return bool(config.get("OPENAI_API_KEY")) and config.get("OPENAI_AUTH_STATUS") is not None

Try / catch

try:
    runtime, client = resolve_runtime(config, depth)
except RuntimeError as e:
    if "no valid OpenAI auth" in str(e):
        rerun_onboarding_auth()  # revalidates token and rewrites status

Prevention

When it happens

Trigger: LAST30DAYS_REASONING_PROVIDER=openai with OPENAI_API_KEY absent, or with the key present but OPENAI_AUTH_STATUS not marked OK (e.g. token failed validation during onboarding, or status was never written).

Common situations: Expired or revoked OpenAI tokens where auth validation failed but the raw key lingers in env; partial onboarding that saved the key but not the status entry; env files copied between machines with mismatched status keys.

Related errors

AI-assisted analysis of mvanhorn/last30days-skill@c7460f6114 (2026-08-15). Data as JSON: /api/errors/ce82de486eeba3a5. Report an issue: GitHub.