feat(llm): add MiniMax-M3 and MiniMax-M2.7 text model coverage - #126
Open
octo-patch wants to merge 1 commit into
Open
feat(llm): add MiniMax-M3 and MiniMax-M2.7 text model coverage#126octo-patch wants to merge 1 commit into
octo-patch wants to merge 1 commit into
Conversation
The MiniMax provider defaulted to MiniMax-M2.5 and its tests exercised MiniMax-M2.5 only, so neither open PR calesthio#120 (M3) nor open PR calesthio#36 (M2.7) covered both current target text model IDs. Expose the supported model set (MiniMax-M3 as default plus MiniMax-M2.7) via a modelIds list and update the unit and integration tests to cover both models, while preserving the explicit LLM_MODEL override.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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: model-add — add built-in/default coverage for both MiniMax-M3 and MiniMax-M2.7 text models while preserving the explicit LLM_MODEL override.
Problem
The MiniMax provider defaulted to
MiniMax-M2.5and its unit and integration tests exercisedMiniMax-M2.5only. The current target text model set requires bothMiniMax-M3andMiniMax-M2.7. Open PR #120 updates the default and fixtures to M3, and open PR #36 updates them to M2.7, so neither change alone covers both target model IDs.Changes
lib/llm/minimax.mjs: IntroduceMINIMAX_DEFAULT_MODEL(MiniMax-M3) andMINIMAX_MODEL_IDS(['MiniMax-M3', 'MiniMax-M2.7']). The default model is the first entry of the supported list, and the provider now exposesthis.modelIds. An explicitconfig.model/LLM_MODELoverride still wins.test/llm-minimax.test.mjs: Update unit tests to assert the default isMiniMax-M3, thatmodelIdscontains bothMiniMax-M3andMiniMax-M2.7, and that an explicitMiniMax-M2.7model is honored without changing the supported set. Update request/response fixtures fromMiniMax-M2.5toMiniMax-M3.test/llm-minimax-integration.test.mjs: Cover bothMiniMax-M3andMiniMax-M2.7against the real API (skipped withoutMINIMAX_API_KEY)..env.exampleandREADME.md: DocumentMiniMax-M3as the default and noteMiniMax-M2.7is also supported.The target text model IDs (
MiniMax-M3,MiniMax-M2.7) come from the current model configuration; no model names, context windows, or URLs are hardcoded beyond the supported set.Checks
node --test test/llm-minimax.test.mjs— 11/11 pass (unit + factory tests).MINIMAX_API_KEY).