feat: upgrade MiniMax default model to M3#78
Open
octo-patch wants to merge 1 commit into
Open
Conversation
Update placeholder example and test fixtures to use MiniMax-M3 as the new flagship model. The legacy MiniMax-M2.7-highspeed fixture is retained to keep coverage for the highspeed variant. Co-Authored-By: Octopus <liyuan851277048@icloud.com>
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 join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Refresh the MiniMax model references to point at the new flagship
MiniMax-M3. Since the project takes the model name as free-text input rather than a model list, this PR updates only the user-facing placeholder hint and the test fixtures that drive the MiniMax routing tests.Changes
src/renderer/components/settings/LLMSection.tsx: Update the model input placeholder fromMiniMax-M2.7toMiniMax-M3so new users see the latest model as the suggested example.tests/main/ai/llm-router.test.ts: Update fourMiniMax-M2.7fixtures toMiniMax-M3. TheMiniMax-M2.7-highspeedfixture is intentionally kept to preserve coverage for the highspeed variant, which is still available on the platform.Why
MiniMax-M3is the new flagship model with a 512K context window, 128K max output, and image input support across both OpenAI-compatible and Anthropic-compatible interfaces. Surfacing it as the placeholder example makes the recommended default obvious for new users while keeping all existing free-text model names usable.Testing
pnpm test— 63 tests passing (3 skipped), including all minimax routing/header/parsing casesnpx tsc --noEmit— no type errors