Add MiniMax provider preset to the subprocess runner - #256
Open
octo-patch wants to merge 1 commit into
Open
Conversation
Mirror the existing GLM shortcut with a MiniMax preset: map the minimax, minimax-m3, and minimax-m2.7 model aliases to their canonical MiniMax-M3 and MiniMax-M2.7 IDs, and select the global or China Anthropic-compatible endpoint (append -cn for China). Centralize the --model argument handling behind resolveModelArg() and route the base URL in buildChildEnv().
|
Codex usage limits have been reached for code reviews. Please check with the admins of this repo to increase the limits by adding credits. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Reason: The subprocess runner had a first-class GLM provider shortcut but no MiniMax provider preset.
What changed
Adds a MiniMax provider preset to the Claude subprocess runner, mirroring the existing GLM shortcut in
src/runner.ts.resolveMinimaxModel()maps themodelsetting aliasesminimax,minimax-m3, andminimax-m2.7to their canonical model IDsMiniMax-M3andMiniMax-M2.7(the bareminimaxalias resolves to the latest,MiniMax-M3).https://api.minimax.io/anthropicby default, or the China endpointhttps://api.minimaxi.com/anthropicwhen a-cnsuffix is appended to the alias (e.g.minimax-m3-cn).buildChildEnv()setsANTHROPIC_BASE_URLfor the selected endpoint; the existingapisetting continues to supplyANTHROPIC_AUTH_TOKEN.--modelargument sites are centralized behind a newresolveModelArg()helper. It preserves the existing behavior (GLM uses the provider default with no--modelflag; other models pass through unchanged) and rewrites MiniMax aliases to their canonical model IDs.model/apivalues incommands/config.mdandcommands/start.md.Checks
bun test— 145 pass, 3 pre-existing unrelated failures insessionFiles(present before this change).bun test src/__tests__/provider-preset.test.ts— 11 pass (new tests for the preset resolution and child-env routing).