Skip to content

Conversation

@mohammad154
Copy link
Contributor

@mohammad154 mohammad154 commented Sep 1, 2025

Related GitHub Issue

Closes: #7295

Roo Code Task Context (Optional)

Description

This PR adds support for the Qwen/Qwen3-235B-A22B-Thinking-2507 model by defining its properties in the Chutes provider configuration.

The implementation involves adding a new entry to the model map in packages/types/src/providers/chutes.ts. This entry includes the model's maxTokens, contextWindow, pricing information (inputPrice, outputPrice), and other relevant metadata. This allows the model to be recognized and utilized throughout the Roo Code application.

Test Procedure

Manual testing was performed to verify the changes:

  1. Run the application locally after a fresh build.
  2. Navigate to the model selection dropdown menu.
  3. Verify that "Qwen/Qwen3-235B-A22B-Thinking-2507" appears in the list of available models.
  4. Select the model and attempt to send a request to confirm that the application correctly uses the new configuration.
  5. Check the application's cost estimation logic (if applicable) to ensure the new pricing is correctly calculated.

No new automated tests were added as this change is purely a configuration update.

Pre-Submission Checklist

  • Issue Linked: This PR is linked to an approved GitHub Issue (see "Related GitHub Issue" above).
  • Scope: My changes are focused on the linked issue (one major feature/fix per PR).
  • Self-Review: I have performed a thorough self-review of my code.
  • Testing: New and/or updated tests have been added to cover my changes (if applicable).
  • Documentation Impact: I have considered if my changes require documentation updates (see "Documentation Updates" section below).
  • Contribution Guidelines: I have read and agree to the [Contributor Guidelines](https://www.google.com/search?q=/CONTRIBUTING.md).

Screenshots / Videos

N/A. This is a code-only change with no direct UI impact other than the new model name appearing in a list.

Documentation Updates

Yes, the official documentation listing supported models should be updated to include Qwen/Qwen3-235B-A22B-Thinking-2507.

Additional Notes

None.

Get in Touch

Discord username:
mohammaddanaee


Important

Add Qwen/Qwen3-235B-A22B-Thinking-2507 model configuration to chutes.ts with specific properties and pricing.

  • Model Addition:
    • Adds Qwen/Qwen3-235B-A22B-Thinking-2507 to chutesModels in chutes.ts.
    • Sets maxTokens to 32768 and contextWindow to 262144.
    • Configures inputPrice as 0.077968332 and outputPrice as 0.31202496.
    • Describes as "Qwen3 235B A22B Thinking 2507 model with 262K context window."

This description was created by Ellipsis for c121ecf. You can customize this summary. It will automatically update as commits are pushed.

@dosubot dosubot bot added size:XS This PR changes 0-9 lines, ignoring generated files. Documentation Improvements or additions to documentation Enhancement New feature or request labels Sep 1, 2025
Copy link
Contributor

@roomote roomote bot left a comment

Choose a reason for hiding this comment

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

Thank you for your contribution! I've reviewed the changes and found several critical issues that need to be addressed before this can be merged.

@roomote
Copy link
Contributor

roomote bot commented Sep 1, 2025

Important: This PR claims to close issue #4225, but that issue is about "AI-Powered Commit Message Generation" which is completely unrelated to adding a model configuration. Please update the PR description to either:

  1. Link to the correct issue for adding this model, or
  2. Remove the issue reference if there is no associated issue, or
  3. Create a new issue for this model addition and link to it

This needs to be corrected to maintain proper issue tracking.

@hannesrudolph hannesrudolph added the Issue/PR - Triage New issue. Needs quick review to confirm validity and assign labels. label Sep 1, 2025
…ChutesModelId union type declared at the top of the file
@dosubot dosubot bot added size:S This PR changes 10-29 lines, ignoring generated files. and removed size:XS This PR changes 0-9 lines, ignoring generated files. labels Sep 1, 2025
| "zai-org/GLM-4.5-Air"
| "zai-org/GLM-4.5-FP8"
| "moonshotai/Kimi-K2-Instruct-75k"
"Qwen/Qwen3-235B-A22B-Thinking-2507"
Copy link
Collaborator

Choose a reason for hiding this comment

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

I think it's already there, above

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Yes, I added it a few minutes ago

Copy link
Contributor Author

@mohammad154 mohammad154 left a comment

Choose a reason for hiding this comment

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

I'm fix all errors !

@mohammad154 mohammad154 requested a review from mrubens September 1, 2025 17:00
@daniel-lxs daniel-lxs moved this from Triage to PR [Needs Prelim Review] in Roo Code Roadmap Sep 2, 2025
@hannesrudolph hannesrudolph added PR - Needs Preliminary Review and removed Issue/PR - Triage New issue. Needs quick review to confirm validity and assign labels. labels Sep 2, 2025
Copy link
Member

@daniel-lxs daniel-lxs left a comment

Choose a reason for hiding this comment

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

Thank you @mohammad154 for your contribution!

@dosubot dosubot bot added the lgtm This PR has been approved by a maintainer label Sep 2, 2025
@daniel-lxs daniel-lxs moved this from PR [Needs Prelim Review] to PR [Needs Review] in Roo Code Roadmap Sep 2, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Documentation Improvements or additions to documentation Enhancement New feature or request lgtm This PR has been approved by a maintainer PR - Needs Review size:S This PR changes 10-29 lines, ignoring generated files.

Projects

Archived in project

Development

Successfully merging this pull request may close these issues.

4 participants