Upgrade MiniMax agent to M3 model#72
Open
octo-patch wants to merge 1 commit into
Open
Conversation
Bump the bundled MiniMax API agent default from `MiniMax-M2.7` to the newer `MiniMax-M3` model in `config.toml`, the `config.local.toml.example` template, and the README. The "Available models" lists keep `MiniMax-M2.7` and `MiniMax-M2.7-highspeed` as fallback options and drop the older `MiniMax-M2.5` / `MiniMax-M2.5-highspeed`, so users get the latest model by default while retaining the previous generation if needed. No code, dependency, or endpoint changes — `base_url`, temperature clamping, and the `MINIMAX_API_KEY` env var are untouched. 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Bumps the bundled MiniMax API agent default from
MiniMax-M2.7toMiniMax-M3inconfig.toml, theconfig.local.toml.exampletemplate, and the README. The "Available models" list keepsMiniMax-M2.7andMiniMax-M2.7-highspeedas fallback options and drops the olderMiniMax-M2.5/MiniMax-M2.5-highspeed, so users get the newest model by default while still being able to pin to the previous generation.Why
MiniMax-M3is MiniMax's current flagship model — same OpenAI-compatible endpoint, sameMINIMAX_API_KEY, so the upgrade is a one-line config flip plus matching doc updates. Keeping M2.7 in the docs gives users an easy fallback if they have specific reasons (cost, latency, behavior) to stay on the previous generation.What changed
config.toml—[agents.minimax].modelset toMiniMax-M3config.local.toml.example— model in the commented[agents.minimax]block + "Available models" comment updated toM3 (default) / M2.7 / M2.7-highspeedREADME.md— sample config block, "uses the MiniMax-M3 model" sentence, and "Available models" line updatedNo code, dependency, or endpoint changes —
base_url(https://api.minimax.io/v1), the temperature clamp inwrapper_api.py, and theMINIMAX_API_KEYenv var are all untouched. Launch scripts (start_minimax.sh/start_minimax.bat) are unaffected because they read the model fromconfig.toml.Test plan
config.tomlparses withtomllibandagents.minimax.model == "MiniMax-M3"python -m py_compile run.py app.py wrapper_api.py config_loader.pycleanpytest tests/— 42 passed (config overrides, router, wrapper MCP config, archive feature, channel fallback)rg -E "MiniMax-(M1|M2[^.]|M2\.1|M2\.5)"returns no matches — all older variants removed