OpenAI compatible reasoning effort

[cte]

Context

Implementation

Screenshots

before	after

How to Test

Get in Touch

---

Important

Adds reasoning effort feature to OpenAI handler with UI support and localization updates.

• Behavior:
  • Adds enableReasoningEffort option to ProviderSettings in types.ts and roo-code.d.ts.
  • Updates providerSettingsSchema in schemas/index.ts to include enableReasoningEffort.
  • Implements reasoning effort logic in OpenAiHandler in openai.test.ts.
• UI:
  • Adds checkbox for enableReasoningEffort in ApiOptions.tsx.
  • Updates ApiOptions.test.tsx to test new checkbox behavior.
• Localization:
  • Updates multiple language files (e.g., settings.json in locales/ja, locales/ko, locales/pl, etc.) to include setReasoningLevel translation.
• Dependencies:
  • Adds @types/node-cache to package.json.

^{This description was created by for d8406ac. You can customize this summary. It will automatically update as commits are pushed.}

[changeset-bot]

⚠️ No Changeset found

Latest commit: d8406ac

Merging this PR will not cause a version bump for any packages. If these changes should not result in a new version, you're good to go. If these changes should result in a version bump, you need to add a changeset.

This PR includes no changesets

When changesets are added to this PR, you'll see the packages that this PR includes changesets for and the associated semver types

Click here to learn what changesets are, and how to add one.

Click here if you're a maintainer who wants to add a changeset to this PR

[ellipsis-dev]

The pull request contains multiple types of changes, including adding a new feature (reasoning effort), tests, and translations for multiple languages. To improve clarity and reviewability, consider splitting the translations into a separate pull request from the feature and tests. This will allow for more focused review and testing of each aspect.

[ellipsis-dev]

The new key setReasoningLevel uses the phrase 'Включить усилие рассуждения'. For consistency with the label in reasoningEffort (which uses 'Усилия по рассуждению модели'), consider updating it to 'Включить усилия рассуждения'.

Suggested change

	"setReasoningLevel": "Включить усилие рассуждения"
	"setReasoningLevel": "Включить усилия рассуждения"