HKUDS/nanobot · error · ValueError

Azure OpenAI requires api_base in config.

Error message

Azure OpenAI requires api_base in config.

What it means

Validation in _resolve_provider_setup: the resolved backend is azure_openai, which has no default endpoint, yet no providers.azure.api_base (Azure resource endpoint URL) is configured. Azure OpenAI clients cannot construct a deployment URL without it, so setup is rejected before any client is built.

Solutions

1. Set providers.azure.apiBase to your Azure OpenAI resource endpoint (https://<resource>.openai.azure.com)
2. Verify the provider name in the config maps to the Azure entry that carries api_base

When it happens

Trigger: Thrown at nanobot/providers/factory.py:108 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of HKUDS/nanobot@42f37dc4c0 (2026-08-26). Data as JSON: /api/errors/3ca8929d7b46dc76. Report an issue: GitHub.

Appendix: source

Thrown at nanobot/providers/factory.py:108

        if not p.api_base:
            raise ValueError(f"Provider '{provider_name}' requires api_base in config.")
        spec = create_dynamic_spec(
            provider_name,
            display_name=(p.display_name or "") if p else "",
            thinking_style=(p.thinking_style or "") if p else "",
        )
    if spec and spec.is_transcription_only:
        raise ValueError(f"Provider '{provider_name}' only supports transcription.")
    backend = spec.backend if spec else "openai_compat"
    if p and p.proxy and backend not in {"openai_compat", "openai_codex", "xai_grok"}:
        raise ValueError(
            f"providers.{provider_name}.proxy is only supported for "
            "OpenAI-compatible providers, OpenAI Codex, and xAI Grok."
        )

    if backend == "azure_openai":
        if not p or not p.api_base:
            raise ValueError("Azure OpenAI requires api_base in config.")
    elif (
        backend == "openai_compat"
        and spec
        and spec.is_direct
        and not spec.default_api_base
        and not (p and p.api_base)
    ):
        raise ValueError(f"Provider '{provider_name}' requires api_base in config.")
    elif backend in {"anthropic", "openai_compat"} and not (
        backend == "openai_compat" and model.startswith("bedrock/")
    ):
        needs_key = not (p and p.api_key)
        exempt = spec and (spec.is_oauth or spec.is_local or spec.is_direct)
        if needs_key and not exempt:
            raise ValueError(f"No API key configured for provider '{provider_name}'.")

    return _ProviderSetup(
        model=model,

View on GitHub (pinned to 42f37dc4c0)