Skip to content

Conversation

@raulcorreia7
Copy link

@raulcorreia7 raulcorreia7 commented Oct 5, 2025

Adds the missing zai-org/GLM-4.6-turbo model to the Chutes provider configuration. Closes #8515


Important

Add zai-org/GLM-4.6-turbo model to Chutes provider configuration in chutes.ts.

  • Models:
    • Add zai-org/GLM-4.6-turbo to ChutesModelId in chutes.ts.
    • Define zai-org/GLM-4.6-turbo in chutesModels with 32768 max tokens, 202752 context window, no image support, no prompt cache, and 1.15 input / 3.25 output price.

This description was created by Ellipsis for 9888efae3b46d5a16fcf89bd80d210dcaa4121a6. You can customize this summary. It will automatically update as commits are pushed.

@dosubot dosubot bot added size:S This PR changes 10-29 lines, ignoring generated files. Enhancement New feature or request labels Oct 5, 2025
@hannesrudolph
Copy link
Collaborator

@raulcorreia7 its free?

@hannesrudolph hannesrudolph added the Issue/PR - Triage New issue. Needs quick review to confirm validity and assign labels. label Oct 5, 2025
@raulcorreia7 raulcorreia7 force-pushed the feature/8515-add-glm-4.6-turbo branch from 9888efa to 65f4d63 Compare October 5, 2025 00:48
@raulcorreia7
Copy link
Author

raulcorreia7 commented Oct 5, 2025

@hannesrudolph , no.

I think its a high QUANT/high TPS model.

Worth it with the 20$ subscription

https://chutes.ai/app/chute/69f319a7-7f25-5cce-ae30-68b30fd5ec5d?tab=stats

@raulcorreia7 raulcorreia7 force-pushed the feature/8515-add-glm-4.6-turbo branch from 65f4d63 to 5d36ecf Compare October 5, 2025 00:49
@hannesrudolph
Copy link
Collaborator

You have $0 for the price

@raulcorreia7
Copy link
Author

I could open a seperate issue to update all model prices.

You can query https://llm.chutes.api/v1/models and extract all the pricing.
I didn't do it here because that's overdoing it

@raulcorreia7
Copy link
Author

Please check again, I force pushed.
The agent I was using was introducing bad new lines in other model locations.

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.

I found some issues that need attention. See inline comments.

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.

I found some issues that need attention.

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.

I found some issues that need attention. See inline comments.

@raulcorreia7 raulcorreia7 force-pushed the feature/8515-add-glm-4.6-turbo branch 4 times, most recently from 40a7c18 to d42a3d7 Compare October 5, 2025 01:10
@raulcorreia7 raulcorreia7 force-pushed the feature/8515-add-glm-4.6-turbo branch from d42a3d7 to 1f3ad22 Compare October 5, 2025 01:12
@raulcorreia7
Copy link
Author

I was struggling with your linter/formatter.
It seems you guys merged #8156
It should be coherent now

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.

I found some issues that need attention.

raulcorreia7 and others added 2 commits October 5, 2025 03:22
Co-authored-by: roomote[bot] <219738659+roomote[bot]@users.noreply.github.com>
@dosubot dosubot bot added size:M This PR changes 30-99 lines, ignoring generated files. and removed size:S This PR changes 10-29 lines, ignoring generated files. labels Oct 5, 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.

I found some issues that need attention.

@raulcorreia7
Copy link
Author

@hannesrudolph should be complete IMO.

do a final review

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.

I found some issues that need attention.

raulcorreia7 and others added 2 commits October 5, 2025 04:13
Co-authored-by: roomote[bot] <219738659+roomote[bot]@users.noreply.github.com>
Co-authored-by: roomote[bot] <219738659+roomote[bot]@users.noreply.github.com>
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.

I found some issues that need attention.

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.

I found some issues that need attention.

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.

I found some issues that need attention.

Co-authored-by: roomote[bot] <219738659+roomote[bot]@users.noreply.github.com>
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.

No new blocking issues. One minor test enhancement suggestion to improve regression coverage for the new model.

…atch mapping/regression errors beyond temperature
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.

One minor test enhancement suggestion to improve regression coverage for the new model.

const model = chutesModels["zai-org/GLM-4.6-turbo"]
expect(model.maxTokens).toBe(32768)
expect(model.contextWindow).toBe(202752)
expect(model.supportsImages).toBe(false)
Copy link
Contributor

Choose a reason for hiding this comment

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

[P3] Test coverage: Add a createMessage param-passthrough test specifically for "zai-org/GLM-4.6-turbo". The suite already verifies DeepSeek R1 and a generic non‑DeepSeek model; asserting this model’s call (model id, max_tokens 32768, temperature 0.5, stream true, stream_options { include_usage: true }) would catch mapping regressions that the generic case might miss.

…ct value validation

- Add compile-time assertion ensuring GLM-4.6-turbo is part of ChutesModelId
- Update test to use modelId variable for better type safety
- Add comprehensive validation of all model properties with exact values
- Change description formatting to multi-line style for consistency
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.

I found some issues that need attention.

Co-authored-by: roomote[bot] <219738659+roomote[bot]@users.noreply.github.com>
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.

I found some issues that need attention.

}),
)
// Strengthen test by also asserting the selected model.info matches the static config to catch mapping/regression errors beyond temperature
expect(model.info).toEqual(expect.objectContaining(chutesModels[testModelId]))
Copy link
Contributor

Choose a reason for hiding this comment

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

[P3] Test duplication: the GLM-4.6-turbo config assertions repeat patterns used elsewhere. Consider a small helper to keep assertions consistent and reduce noise across tests (e.g., expectModelInfo(model.info, chutesModels[testModelId])).

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.

I found some issues that need attention.

model: modelId,
max_tokens: modelInfo.maxTokens, // Should be 32768
temperature: 0.5, // Default temperature for non-DeepSeek models
messages: expect.arrayContaining([{ role: "system", content: systemPrompt }]),
Copy link
Contributor

Choose a reason for hiding this comment

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

[P3] Strengthen assertion: also verify the user message is passed through to the OpenAI client to catch regressions in message composition for non-DeepSeek models (in addition to the system prompt). Consider asserting arrayContaining includes both the system and user entries.

@mrubens mrubens closed this Oct 27, 2025
@github-project-automation github-project-automation bot moved this from Triage to Done in Roo Code Roadmap Oct 27, 2025
@github-project-automation github-project-automation bot moved this from New to Done in Roo Code Roadmap Oct 27, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Enhancement New feature or request Issue/PR - Triage New issue. Needs quick review to confirm validity and assign labels. size:M This PR changes 30-99 lines, ignoring generated files.

Projects

Archived in project

Development

Successfully merging this pull request may close these issues.

Add missing GLM-4.6-turbo model to Chutes provider

3 participants