refactor(llm): collapse Endpoint to path-only; require ModelRef.baseURL

Push URL host knowledge from `Endpoint` (route layer) up to `model.baseURL`
(provider helper layer). The route just composes a path onto whatever
host the model already carries.

Endpoint:
- `Endpoint<Body>` shrinks to `{ path }`. No more `default`, `baseURL`,
  or `required` fallback fields.
- `Endpoint.path(value)` replaces the old `Endpoint.baseURL({...})` factory.
- `Endpoint.render()` is now sync — `${model.baseURL}${path}` plus query
  params. No fallback chain, no Effect wrapper.

ModelRef:
- `ModelRef.baseURL: Schema.String` (was optional). Every materialized
  model carries a host.
- `RouteModelInput.baseURL?: string` stays optional so route defaults
  can supply a canonical URL; routes without a default tighten it.

Provider helpers:
- Each protocol exports a `DEFAULT_BASE_URL` constant and bakes it into
  `route.defaults.baseURL`. Provider helpers don't need to set baseURL.
- Azure uses a new `AtLeastOne<T>` helper from `auth-options.ts` to
  require either `resourceName` or `baseURL` at the type level.
- Bedrock provider computes baseURL from `region` at construction time.
- OpenAI-compatible profiles now have required (not optional) `baseURL`
  in their type — all 9 already supplied one.
- The `defaultBaseURL: string | false` knob on protocol endpoint
  factories is gone.

Effects:
- Forgetting baseURL is now caught at compile time (TS) or model
  construction time (modelWithDefaults runtime check), not request time.
- `Endpoint.render` no longer needs Effect wrapping in the transport
  hot path.
This commit is contained in:
Kit Langton
2026-05-07 12:03:28 -04:00
parent 32ad9cbc8c
commit c5e20033ec
30 changed files with 167 additions and 196 deletions
@@ -7,7 +7,7 @@ const types = (events: ReadonlyArray<{ readonly type: string }>) => events.map((
describe("LLMNativeEvents", () => {
test("synthesizes text and reasoning boundaries around native deltas", () => {
const events = LLMNativeEvents.toSessionEvents([
{ type: "request-start", id: "req_1", model: LLM.model({ id: "gpt-5", provider: "openai", route: "openai-responses" }) },
{ type: "request-start", id: "req_1", model: LLM.model({ id: "gpt-5", provider: "openai", route: "openai-responses", baseURL: "https://api.openai.com/v1" }) },
{ type: "step-start", index: 0 },
{ type: "text-delta", text: "Hello" },
{ type: "text-delta", text: "!" },