Audit Nextbit provider catalog - #1869
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
Warning Review limit reachedNext included review available in 34 minutes. View limit detailsLimit details: You’ve used the included review currently available. You've used all free OSS reviews for now. Wait for the free limit to reset to keep reviewing this public repository. Review configuration: ⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (19)
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. Comment |
Dependency Review✅ No vulnerabilities or license issues or OpenSSF Scorecard issues found.Scanned FilesNone |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: a58b733392
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| "links": [{ "title": "Weights", "kind": "weights", "url": "https://huggingface.co/Gryphe/MythoMax-L2-13b" }], | ||
| "details": [], "benchmarks": [], "family_id": null, "page_notice": null, "model_type": null, "knowledge_cutoff": null, | ||
| "limits": { "context": 4096, "input": 4096, "output": 4096 }, "modalities": { "input": ["text"], "output": ["text"] }, | ||
| "reasoning": { "supported": true, "options": [] }, "capabilities": { "attachment": false, "tool_call": true, "structured_output": true, "temperature": true, "streaming": true, "web_search": false }, |
There was a problem hiding this comment.
The only verification recorded here is for Nextbit's hosted route, yet this canonical MythoMax record asserts provider-independent reasoning, tool-calling, and structured-output support; the same copied flags appear on the other four new canonical models. This misclassifies capabilities for these models outside Nextbit—comparable base-model records leave these fields unknown—and duplicates claims already represented correctly in Nextbit's provider route. Leave the canonical flags unknown unless an upstream model source verifies them.
AGENTS.md reference: packages/data/catalog/AGENTS.md:L14-L16
Useful? React with 👍 / 👎.
| "service_tiers": [], | ||
| "sources": [], | ||
| "auth_env": ["NEXTBIT_API_KEY"], | ||
| "api_formats": ["openai.chat.completions", "openai.completions"], |
There was a problem hiding this comment.
Every verified Nextbit model route in this change exposes only openai.chat.completions, and the added API-reference provenance specifically documents Chat Completions, so adding openai.completions at provider level advertises an endpoint that no callable route or cited source supports. Provider-metadata consumers can consequently present the legacy /v1/completions API as compatible even though the audited catalog only establishes /v1/chat/completions.
AGENTS.md reference: packages/data/catalog/AGENTS.md:L14-L16
Useful? React with 👍 / 👎.
1 participant
Summary
Validation
Created with Codex