feat(llm): provider packages own model request construction

Provider packages in @opencode-ai/llm/providers/* now implement a uniform
ProviderPackage contract: model(modelID, settings) => Model. SessionRunnerModel
becomes provider-agnostic: it resolves a package specifier, folds catalog
settings, credentials, and transport overlays into one Settings object, and
delegates request construction to the package.

- llm: add ProviderPackage (Settings, Definition, define), flat model(id,
  config) constructors on the openai-responses, anthropic-messages, and
  openai-compatible-chat protocols, contract-shaped model exports on the
  openai, anthropic, and openai-compatible providers, and a new
  providers/openai/codex entry point that targets the ChatGPT codex backend
  and sets the chatgpt-account-id header from settings.accountID.
- schema: Provider.Native gains optional package.
- core: SessionRunnerModel loads packages through a static built-in map
  (dynamic import for foreign specifiers) and applies one settings fold;
  the ChatGPT conditional is deleted from the runner. The OpenAI plugin's
  catalog transform now assigns the codex package to eligible models when a
  ChatGPT connection is active, alongside the existing eligibility and cost
  rewrites.
- llm schema: hoist ToolResultValue union out of its Object.assign self
  reference; the previous shape only typechecked under lucky check ordering
  and broke under core's typecheck with the new import graph.

Closes #34765

packages/schema/src/provider.ts

@@ -34,6 +34,7 @@ export const AISDK = Schema.Struct({
 export interface Native extends Schema.Schema.Type<typeof Native> {}
 export const Native = Schema.Struct({
   type: Schema.Literal("native"),
+  package: Schema.String.pipe(optional),
   url: Schema.String.pipe(optional),
   settings: Schema.Record(Schema.String, Schema.Unknown),
 }).annotate({ identifier: "Provider.Native" })