HKUDS/DeepTutor · critical · LLMConfigError

OpenAI API key is not configured. Set it in Settings > Catal

Error message

OpenAI API key is not configured. Set it in Settings > Catalog, or select a local provider such as Ollama.

What it means

After resolving model and URL, the config loader enforces authentication for official OpenAI: if the provider is openai, mode is standard (not oauth), and the api_key is one of the placeholder values ('', 'no-key', 'sk-no-key-required'), it raises LLMConfigError with actionable guidance. Local providers like Ollama are explicitly offered as the alternative.

Source

Thrown at deeptutor/services/llm/config.py:187

def _get_llm_config_from_resolver() -> LLMConfig:
    """Resolve LLM config from the TutorBot-style runtime adapter."""
    resolved = resolve_llm_runtime_config()
    if not resolved.model:
        raise LLMConfigError(
            "No active LLM model is configured. Please set it in Settings > Catalog."
        )
    if not resolved.effective_url and resolved.provider_mode != "oauth":
        raise LLMConfigError(
            "No effective LLM endpoint resolved. Please configure base_url or provider defaults."
        )
    is_placeholder_key = resolved.api_key in {"", "no-key", "sk-no-key-required"}
    if (
        resolved.provider_name == "openai"
        and resolved.provider_mode == "standard"
        and is_placeholder_key
    ):
        raise LLMConfigError(
            "OpenAI API key is not configured. Set it in Settings > Catalog, "
            "or select a local provider such as Ollama."
        )
    return LLMConfig(
        model=resolved.model,
        api_key=resolved.api_key,
        base_url=resolved.base_url,
        effective_url=resolved.effective_url,
        binding=resolved.binding,
        provider_name=resolved.provider_name,
        provider_mode=resolved.provider_mode,
        api_version=resolved.api_version,
        extra_headers=resolved.extra_headers,
        reasoning_effort=resolved.reasoning_effort,
        context_window=resolved.context_window,
    )

View on GitHub (pinned to 3e82f13042)

Solutions

1. Set the OpenAI key in Settings > Catalog or via OPENAI_API_KEY.
2. If you intended local inference, switch the provider to Ollama (or set its base_url) instead of OpenAI.
3. Remove placeholder strings like 'sk-no-key-required' from settings templates.
4. For OAuth flows, set provider_mode to 'oauth' so this check is bypassed.

Example fix

// before
export OPENAI_API_KEY=sk-no-key-required

# after
export OPENAI_API_KEY=sk-...your-real-key...

PLACEHOLDERS = {"", "no-key", "sk-no-key-required"}
resolved = resolve_llm_runtime_config()
if resolved.provider_name == "openai" and resolved.provider_mode == "standard" and resolved.api_key in PLACEHOLDERS:
    raise RuntimeError("Set an OpenAI key or switch to a local provider")
cfg = get_llm_config()

def is_placeholder_key(api_key: str | None) -> bool:
    return (api_key or "") in {"", "no-key", "sk-no-key-required"}

try:
    cfg = get_llm_config()
except LLMConfigError as e:
    if "OpenAI API key is not configured" in str(e):
        prompt_for_openai_key_or_switch_to_ollama()
    raise

When it happens

Trigger: Provider=openai with no API key stored and mode=standard; key still at the shipped placeholder 'sk-no-key-required' from a template settings file; OPENAI_API_KEY unset in the environment fallback.

Common situations: Users running the default profile unchanged; template/docker setups shipping placeholder keys; env var present in one shell but the server launched from another; CI without secrets.

Understand the failure class

Background: "API key is required" / "API key not found" / "No API key was set": the missing-api-key error family across 16 libraries — this error's family across 16 libraries.

Related errors

• Anthropic API key is missing from the active LLM profile.
• Cohere API key is missing from the active LLM profile.
• OpenAI API key is not configured. Set it in Settings > Catal
• PageIndex OSS indexing needs an API-key or local LLM profile
• Model is required for cloud LLM provider

AI-assisted analysis of HKUDS/DeepTutor@3e82f13042 (2026-08-27). Data as JSON: /api/errors/4936bcb2c08faac7. Report an issue: GitHub.