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

This commit is contained in:
2026-05-06 19:09:58 +00:00
parent 8ad0b90f95
commit 5c871242b0
10 changed files with 952 additions and 1178 deletions
+17
View File
@@ -1,5 +1,22 @@
# Changelog
## 2026-05-06 - 2.2.0 - feat(openai)
add getModelSetup() and typed provider options for OpenAI reasoning settings
- export getModelSetup() to return both the model and request-time providerOptions for AI SDK calls
- add typed OpenAI provider options including reasoningEffort and textVerbosity support
- cover providerOptions passthrough for generateText() and streamText() with tests
- update documentation and dependency versions for the new OpenAI provider options workflow
## 2026-05-06 - 2.1.0 - feat(openai)
add first-class OpenAI provider options for request-time reasoning settings
- add `getModelSetup()` returning a model plus AI SDK `providerOptions`
- add typed OpenAI provider options including `reasoningEffort: 'xhigh'` and `textVerbosity`
- keep `getModel()` backward compatible for existing consumers
- document GPT-5.5 xhigh usage and update dependency versions
- add tests proving provider options pass through `generateText()` and `streamText()`
## 2026-04-30 - 2.0.1 - fix(build)
update toolchain configuration and test error handling for stricter TypeScript builds