Results / request.tools-with-reasoning-chat
Function tools with the default reasoning effort
The caller requests a function tool without setting reasoning effort, and Chat Completions rejects the combination.
Bug class: The library sends something the caller didn't ask for
The library adds, drops or renames request fields the caller didn't set, or sends a combination the provider rejects.
Calls fail on current models, or behave differently from what the caller configured.
Requirements
| Level | Id | Check | Requirement | Providers |
|---|---|---|---|---|
| MUST | error-reported | outcome_is_error | The library surfaces the API error or refuses the call through validation before sending it. | All |
Fixtures
| Provider | Tier | any-llm | litellm | pydantic-ai | tanstack-ai | vercel-ai |
|---|---|---|---|---|---|---|
| openai-chat | recorded | ✓ PASS | ✓ PASS | ✓ PASS | – UNSUPPORTED | ✓ PASS |