OpenAIProvider

Constructs the client for a ProviderConfig this provider produced.

config is whatever the caller passed, so implementations must check the type rather than cast — ProviderDescriptor.expectConfig does that and produces the standard mismatch error.

Turns a validated config section into the runtime ProviderConfig for this provider.

The section has already been checked against configSpec, so required fields are present and section.extras holds exactly the declared provider-specific keys that have a value (defaults applied, deprecated aliases resolved). A Left here means something configSpec cannot express (a malformed value, say).

Alternative spellings accepted in provider = "...", folded onto id.

For example Gemini accepts "google". Aliases are matched after the same trim/lowercase canonicalisation as id itself.

What this provider's client implements. Defaults to the full interface.

The OpenAI API base URL used when a provider section sets no baseUrl.

This was DefaultConfig.DEFAULT_OPENAI_BASE_URL in llm4s-core until the provider moved to llm4s-openai (#1132).

The key falls back to llm4s.credentials.openai.apiKey, bound to OPENAI_API_KEY; a section with an auth block uses workload identity federation instead and needs no key.

Canonical id, e.g. ProviderId("openai"). Must be unique within a registry.

Live model discovery, when the provider's API offers it.