feat(models): add o1 model with OpenAI provider - #376
Conversation
Introduced new `o1` model with OpenAI provider support. Configured pricing, context size, and streaming capabilities.
WalkthroughA new entry for the "o1" model, provided by "openai," was added to the exported models array. This entry specifies pricing, context size, streaming capability, and JSON output support. No other changes were made to existing models or interfaces. Changes
Sequence Diagram(s)sequenceDiagram
participant Client
participant ModelsModule
Client->>ModelsModule: Request available models
ModelsModule-->>Client: Return models array (includes new "o1" model)
Possibly related PRs
✨ Finishing Touches
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
|
Claude finished @steebchen's task —— View job Code Review for PR #376Completed comprehensive review of the o1 model addition. Tasks:
Review Summary:The PR adds o1 model configuration following existing patterns. Two critical issues identified:
Overall code quality is good, just needs capability flags corrected to match OpenAI's o1 specifications. Review submitted with detailed inline comments and recommendations. |
![claude[bot]](https://avatars.githubusercontent.com/in/1236702?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review Summary
The o1 model addition follows the existing code patterns and structure well. However, there are two important capability issues that need attention:
- Streaming: o1 models don't support streaming - should be
false - JSON Output: Verify structured output support before enabling
Positive Aspects:
- ✅ Consistent with existing model definitions
- ✅ Pricing appears accurate ($15/1M input, $60/1M output)
- ✅ Context size (200K tokens) is appropriate
- ✅ Proper TypeScript typing maintained
Recommendations:
- Fix the streaming capability to
false - Verify JSON output support or set to
falseif unsupported - Consider adding tests for the new model configuration
The overall implementation quality is good - just needs the capability flags corrected to match OpenAI's o1 model specifications.
| inputPrice: 15.0 / 1e6, | ||
| outputPrice: 60.0 / 1e6, | ||
| contextSize: 200000, | ||
| streaming: true, |
There was a problem hiding this comment.
🚨 Streaming Support Issue: OpenAI's o1 models do not support streaming responses. This should be set to false.
According to OpenAI's documentation, o1 models generate responses in a single completion and don't support streaming chunks. Setting this to true may cause runtime errors or unexpected behavior.
| streaming: true, | ||
| }, | ||
| ], | ||
| jsonOutput: true, |
There was a problem hiding this comment.
While o1 models can generate JSON in their responses, they may have limitations with OpenAI's structured output features (like response_format: { "type": "json_object" }). You may want to test this capability or set to false if unsupported to avoid runtime issues.
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
packages/models/src/models.ts (1)
139-152: Consider groupingo-series models together
For consistency and readability, you might reorder entries so that allo-series models (o1,o3,o3-mini) appear consecutively under the OpenAI provider.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
packages/models/src/models.ts(1 hunks)
⏰ Context from checks skipped due to timeout of 90000ms (4)
- GitHub Check: claude-review
- GitHub Check: build / run
- GitHub Check: e2e / run
- GitHub Check: test / run
🔇 Additional comments (1)
packages/models/src/models.ts (1)
139-152: Validateo1model’s pricing and context parameters
Ensure the inputPrice (15.0/1e6), outputPrice (60.0/1e6), and contextSize (200000) correspond to OpenAI’s official o1 model specifications.What are the official input/output token prices and maximum context size for OpenAI’s “o1” model according to the latest OpenAI documentation?
1 participant
Introduced new
o1model with OpenAI provider support. Configured pricing, context size, and streaming capabilities.Summary by CodeRabbit