feat(openai): add getModelSetup() and typed provider options for OpenAI reasoning settings

readme.hints.md

@@ -6,6 +6,7 @@ The package is a **provider registry** built on the Vercel AI SDK (`ai` v6). The
 
 ### Core Entry (`ts/`)
 - `getModel(options)` → returns `LanguageModelV3` for any supported provider
+- `getModelSetup(options)` → returns `{ model, providerOptions }` for request-time AI SDK provider options
 - Providers: anthropic, openai, google, groq, mistral, xai, perplexity, ollama
 - Anthropic prompt caching via `wrapLanguageModel` middleware (enabled by default)
 - Custom Ollama provider implementing `LanguageModelV3` directly (for think, num_ctx support)
@@ -19,11 +20,11 @@ The package is a **provider registry** built on the Vercel AI SDK (`ai` v6). The
 
 ## Dependencies
 
-- `ai` ^6.0.116 — Vercel AI SDK core
+- `ai` ^6.0.175 — Vercel AI SDK core
 - `@ai-sdk/*` — Provider packages (anthropic, openai, google, groq, mistral, xai, perplexity)
-- `@ai-sdk/provider` ^3.0.8 — LanguageModelV3 types
-- `@anthropic-ai/sdk` ^0.78.0 — Direct SDK for research (web search tool)
-- `openai` ^6.25.0 — Direct SDK for audio TTS and image generation/editing
+- `@ai-sdk/provider` ^3.0.10 — LanguageModelV3 types
+- `@anthropic-ai/sdk` ^0.95.0 — Direct SDK for research (web search tool)
+- `openai` ^6.36.0 — Direct SDK for audio TTS and image generation/editing
 - `@push.rocks/smartpdf` ^4.1.3 — PDF to PNG conversion for document analysis
 
 ## Build
@@ -40,6 +41,8 @@ The package is a **provider registry** built on the Vercel AI SDK (`ai` v6). The
 - Ollama `think` param goes at request body top level, not inside `options`
 - Qwen models get default temperature 0.55 in the custom Ollama provider
 - `qenv.getEnvVarOnDemand()` returns a Promise — must be awaited in tests
+- OpenAI reasoning options belong in AI SDK `providerOptions`, not model construction options
+- SmartAI accepts OpenAI model IDs as plain strings, including `gpt-5.5`
 
 ## Testing