feat: upgrade MiniMax default model to M3 - #93
Open
octo-patch wants to merge 1 commit into
Open
Conversation
- Add MiniMax-M3 to qingchenyun provider catalog (512K context, 128K output) - Add MiniMax-M3 to feature panel built-in models list (placed before M2.7) - Retain MiniMax-M2.7 as the previous-generation option for compatibility - Remove deprecated MiniMax-M2.5 from the catalog - Update INSTALL_GUIDE / models-cn / wizard docs to reference M3
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 the project's bundled MiniMax model entries to include the latest M3 flagship as the recommended option, while keeping M2.7 around for compatibility. Removes the deprecated M2.5 entry from the qingchenyun (qtcool) provider catalog.
Changes
translations/providers/files/extensions/qingchenyun/provider-catalog.tsMiniMax-M3(contextWindow: 524288,maxTokens: 131072) right afterautoMiniMax-M2.5MiniMax-M2.7as a fallback optiontranslations/panel/feature-panel.jsMiniMax-M3to the built-in recommended models list (before M2.7) so it shows up in the Dashboard model pickerdocs/INSTALL_GUIDE.mdminimax/MiniMax-M2.1tominimax/MiniMax-M3docs/guides/models-cn.mddocs/upstream/wizard.mdM2.5 系列toM3 / M2.7 系列Why
MiniMax M3 is the new flagship model with a 512K context window and 128K max output. Surfacing it in the qingchenyun (qtcool) catalog and the recommended built-ins list lets users pick it directly from the Dashboard, and updating the docs keeps the quick-start examples pointing at a current, supported model name (the old
MiniMax-M2.1reference in INSTALL_GUIDE has been deprecated for a while).The change is intentionally minimal: only the qingchenyun provider catalog and the panel built-ins list (project-owned code) are touched. Translation overlay rules in
translations/extensions/*.jsonkeep their existing left-hand match strings unchanged, since those have to keep matching the upstream OpenClaw source.Testing
node cli/index.mjs status— translations config still loads (158 files, all categories detected)translations/**/*.jsonre-validated withjson.load(no parse errors)provider-catalog.tsandfeature-panel.jssyntax checked.github/workflows/pr-check.yml) covers JSON / shell / python validation