feat: Add DeepSeek R1 support to Chutes provider (#4523) #4525
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
dosubot
bot
added
size:L
![ellipsis-dev[bot]](https://avatars.githubusercontent.com/in/64358?s=60&v=4){kind=small}
daniel-lxs
approved these changes
Jun 10, 2025
Collaborator
|
Looks like some test conflicts unfortunately. Do you mind updating and I'll take another look at approve once it's done? |
- Modified BaseOpenAiCompatibleProvider to expose client as protected - Enhanced ChutesHandler to detect DeepSeek R1 models and parse reasoning chunks - Applied R1 format conversion for message formatting - Set appropriate temperature (0.6) for DeepSeek models - Migrated tests from Jest to Vitest format - Added comprehensive tests for DeepSeek R1 functionality This ensures reasoning chunks are properly separated from regular content when using DeepSeek R1 models via Chutes provider.
Member
|
@mrubens |
mrubens
reviewed
Jun 12, 2025
| protected readonly options: ApiHandlerOptions | ||
|
|
||
| private client: OpenAI | ||
| protected client: OpenAI |
Collaborator
There was a problem hiding this comment.
Is this one necessary to change?
mrubens
approved these changes
Jun 12, 2025
github-project-automation
bot
moved this from PR [Needs Review]
to Done
in Roo Code Roadmap
cte
pushed a commit
that referenced
this pull request
Jun 24, 2025
* feat: Add DeepSeek R1 support to Chutes provider (#4523) - Modified BaseOpenAiCompatibleProvider to expose client as protected - Enhanced ChutesHandler to detect DeepSeek R1 models and parse reasoning chunks - Applied R1 format conversion for message formatting - Set appropriate temperature (0.6) for DeepSeek models - Migrated tests from Jest to Vitest format - Added comprehensive tests for DeepSeek R1 functionality This ensures reasoning chunks are properly separated from regular content when using DeepSeek R1 models via Chutes provider. * feat: Enhance DeepSeek R1 support with <think> tag handling in Chutes provider * fix: Correct temperature retrieval in ChutesHandler to use model's info * fix: Update condition for DeepSeek-R1 model identification in createMessage method --------- Co-authored-by: Daniel Riccio <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Fixes #4523
This PR adds support for DeepSeek R1 models when using the Chutes provider. Previously, when using DeepSeek R1 models via Chutes, the reasoning format wasn't recognized, causing reasoning blocks to be merged with regular content and degrading model performance.
Changes Made
BaseOpenAiCompatibleProviderto expose theclientproperty asprotectedinstead ofprivate, allowing subclasses to access the OpenAI clientChutesHandlerto:delta.reasoningin the streamTesting
Verification of Acceptance Criteria
Checklist
Important
Adds support for DeepSeek R1 models in Chutes provider, handling reasoning formats and temperature settings, with tests migrated to Vitest.
ChutesHandlernow detects DeepSeek R1 models by checking if model ID starts with "deepseek-ai/DeepSeek-R1".delta.reasoningin the stream.BaseOpenAiCompatibleProvider:clientproperty changed from private to protected.ChutesHandler: ImplementscreateMessage()to handle DeepSeek R1 models with<think>tags.getModel()inChutesHandleradjusts temperature for DeepSeek R1 models.chutes.spec.ts.This description was created by
for 9810152e6065c25dd3556866edb981515f7b9c3d. You can customize this summary. It will automatically update as commits are pushed.