feat: upgrade MiniMax default model to M3 - #417
Open
octo-patch wants to merge 1 commit into
Open
Conversation
|
Someone is attempting to deploy a commit to the Daily Team on Vercel. A member of the Team first needs to authorize it. |
- Set MiniMax-M3 as the default model for the voice, task, and UI agent configs - Keep MiniMax-M2.7 / MiniMax-M2.7-highspeed selectable via the *_LLM_MODEL env overrides - Update MiniMax provider unit tests to assert the new default
octo-patch
force-pushed
the
feature/upgrade-minimax-m3
branch
from
June 3, 2026 13:39
799f355 to
c18a3a0
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Upgrade MiniMax provider's default model from
MiniMax-M2.7toMiniMax-M3across the voice, task, and UI agent configs.MiniMax-M2.7andMiniMax-M2.7-highspeedremain selectable via the*_LLM_MODELenv overrides.Changes
MiniMax-M3as the default model inget_voice_llm_config,get_task_agent_llm_config, andget_ui_agent_llm_config(src/gradientbang/utils/llm_factory.py)tests/unit/test_llm_factory_minimax.pyto assert the new defaultMiniMax-M2.7/MiniMax-M2.7-highspeedremain available viaVOICE_LLM_MODEL/TASK_LLM_MODEL/UI_AGENT_LLM_MODELWhy
MiniMax-M3is MiniMax's latest flagship model — 512K context, up to 128K output, and image input support. Upgrading the default lets new deployments benefit immediately without changing env overrides for existing pinned setups.Testing
tests/unit/test_llm_factory_minimax.pyupdated to assert the new default and still pass.