Skip to content

Conversation

@mrubens
Copy link
Collaborator

@mrubens mrubens commented Feb 1, 2025

Important

Add o3-mini-high and o3-mini-low models to OpenAI Native handler with specific reasoning efforts.

  • Models:
    • Add o3-mini-high and o3-mini-low to openAiNativeModels in api.ts with reasoning efforts "high" and "low" respectively.
  • Handlers:
    • Update OpenAiNativeHandler in openai-native.ts to handle o3-mini-high and o3-mini-low in createMessage() and completePrompt().
  • Tests:
    • Modify openai-native.test.ts to test o3-mini with reasoning_effort: "medium".

This description was created by Ellipsis for d047c8b. It will automatically update as commits are pushed.

@changeset-bot
Copy link

changeset-bot bot commented Feb 1, 2025

🦋 Changeset detected

Latest commit: d047c8b

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 1 package
Name Type
roo-cline Patch

Not sure what this means? Click here to learn what changesets are.

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

@mrubens mrubens force-pushed the o3_reasoning_effort branch from ac5688c to d047c8b Compare February 1, 2025 05:52
messages: [{ role: "user", content: prompt }],
}
break
case "o3-mini":
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The logic for handling 'o3-mini', 'o3-mini-low', and 'o3-mini-high' is repeated. Consider extracting this logic into a helper function to reduce redundancy. This is from our Development Standards: https://www.notion.so/Development-Standards-59febcf8ead647fd9c2ec3f60c22f3df?pvs=4#11869ad2d5818094a05ef707e188c0d5

@mrubens mrubens merged commit 65257da into main Feb 1, 2025
5 checks passed
@mrubens mrubens deleted the o3_reasoning_effort branch February 1, 2025 05:55
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants