This repository was archived by the owner on May 15, 2026. It is now read-only.
feat: add DeepSeek V4 model support and fix thinking mode detection - #12176
Draft
ghost wants to merge 1 commit into
Draft
feat: add DeepSeek V4 model support and fix thinking mode detection#12176ghost wants to merge 1 commit into
ghost wants to merge 1 commit into
Conversation
- Add deepseek-v4-0324 model to the DeepSeek provider model list with thinking mode, vision support, and pricing info - Fix thinking mode detection to use preserveReasoning flag from ModelInfo instead of hardcoding model name check for "deepseek-reasoner" - This allows any model with preserveReasoning=true to automatically get thinking mode enabled, including v4 and future models - Add tests for v4 model info and thinking mode behavior Addresses #12174
ghost
mentioned this pull request
|
model names should be |
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
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR attempts to address Issue #12174. Feedback and guidance are welcome.
Changes
1. Add DeepSeek V4 model (
deepseek-v4-0324)packages/types/src/providers/deepseek.tswith:preserveReasoning: true)2. Fix thinking mode detection (root cause of the 400 error)
src/api/providers/deepseek.tsto detect thinking mode via thepreserveReasoningflag on ModelInfo instead of hardcodingmodelId.includes("deepseek-reasoner")preserveReasoning: trueautomatically gets thinking mode enabled, including v4 and any future models3. Tests
deepseek-v4-0324Notes
Interactively review PR in Roo Code Cloud