Skip to content

feat(models): add openai oss models#880

Merged
waleedlatif1 merged 2 commits intostagingfrom
feat/models
Aug 5, 2025
Merged

feat(models): add openai oss models#880
waleedlatif1 merged 2 commits intostagingfrom
feat/models

Conversation

@waleedlatif1
Copy link
Collaborator

Summary

add openai oss models for groq

Type of Change

  • New feature

Testing

Tested manually

Checklist

  • Code follows project style guidelines
  • Self-reviewed my changes
  • Tests added/updated and passing
  • No new warnings introduced
  • I confirm that I have read and agree to the terms outlined in the Contributor License Agreement (CLA)

Screenshots/Videos

Screen.Recording.2025-08-05.at.11.39.59.AM.mov

@vercel
Copy link

vercel bot commented Aug 5, 2025

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name Status Preview Comments Updated (UTC)
sim ✅ Ready (Inspect) Visit Preview 💬 Add feedback Aug 5, 2025 7:21pm
1 Skipped Deployment
Name Status Preview Comments Updated (UTC)
docs ⬜️ Skipped (Inspect) Aug 5, 2025 7:21pm

Copy link
Contributor

@greptile-apps greptile-apps bot left a comment

Choose a reason for hiding this comment

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

Greptile Summary

This PR updates the Groq provider configuration in apps/sim/providers/models.ts to include OpenAI OSS (open source) models and other models available through Groq's inference platform. The changes reflect Groq's expansion from hosting only their proprietary models to providing fast inference for a broader catalog of open-source models.

Key changes include:

  • Updated the default model from groq/meta-llama/llama-4-scout-17b-16e-instruct to openai/gpt-oss-120b
  • Added new OpenAI OSS models with openai/ prefixes (openai/gpt-oss-120b, openai/gpt-oss-20b)
  • Updated existing models to remove groq/ prefixes (e.g., gemma2-9b-it, llama-3.1-8b-instant)
  • Enhanced most models with toolUsageControl: true, indicating improved function calling capabilities
  • Updated pricing across all models with a consistent date of '2025-08-05'

This change integrates with the existing provider system where modelPatterns are used for routing model requests to the appropriate inference provider. The Groq provider now serves as a gateway to multiple model families while maintaining its reputation for fast inference speeds.

Confidence score: 1/5

  • This PR has a critical configuration bug that will break model routing for most of the newly added models
  • Score reflects a fundamental mismatch between model IDs and the pattern matching system used for provider detection
  • Pay close attention to the modelPatterns configuration on lines 450-451 and how it conflicts with the new model naming scheme

1 file reviewed, 1 comment

Edit Code Review Bot Settings | Greptile

@vercel vercel bot temporarily deployed to Preview – docs August 5, 2025 19:15 Inactive
@waleedlatif1 waleedlatif1 merged commit 4880d34 into staging Aug 5, 2025
3 of 4 checks passed
@waleedlatif1 waleedlatif1 deleted the feat/models branch August 5, 2025 19:16
waleedlatif1 added a commit that referenced this pull request Aug 6, 2025
* feat(models): add openai oss models

* fix tool usage control for groq
arenadeveloper02 pushed a commit to arenadeveloper02/p2-sim that referenced this pull request Sep 19, 2025
* feat(models): add openai oss models

* fix tool usage control for groq
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.

1 participant