feat: add MiniMax as LLM provider - #543
Open
octo-patch wants to merge 1 commit into
Open
Conversation
Add MiniMax (M2.7, M2.5, M2.5-highspeed) as a first-class LLM provider using the OpenAI-compatible API at api.minimax.io/v1. - New MiniMaxEngine extending OpenAiEngine with think-tag stripping - Full setup wizard integration (provider selection, model list, API key URL) - Dynamic model fetching via /v1/models endpoint with 7-day cache - Error handling with billing URL and model suggestions - README updated with MiniMax provider config example - 32 unit tests + 3 integration tests
Owner
|
hello @octo-patch please merge master into your branch to solve the confict and i will merge it |
di-sukharev
requested changes
Aug 20, 2026
Owner
There was a problem hiding this comment.
First-class MiniMax support is useful, but this PR conflicts with master, and both the end-to-end and Prettier checks fail. After rebasing, please update the models and endpoint against the current API, and replace tests that read source files and search for strings with behavioral engine/request tests. Live integration tests should be opt-in and must not depend on a secret in regular CI.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
MiniMaxEngineextendingOpenAiEngineusing OpenAI-compatible API atapi.minimax.io/v1Changes
src/engine/minimax.tssrc/commands/config.tsMINIMAXenum value, model list, API key URL, recommended model, validatorsrc/utils/engine.tssrc/utils/errors.tssrc/utils/modelCache.tsfetchMiniMaxModels()with/v1/modelsendpoint, cache integrationsrc/commands/setup.tsREADME.mdminimaxto provider list and config exampletest/unit/minimax.test.tstest/unit/minimax-integration.test.tsUsage
Or use the interactive setup wizard:
oco setup # Select "Other providers..." → "MiniMax (M2.7, M2.5, fast inference)"Test plan
npm run test -- test/unit/minimax.test.ts)MINIMAX_API_KEY=... npm run test -- test/unit/minimax-integration.test.ts)test/unit/config.test.ts,test/unit/removeContentTags.test.ts)oco setup→ select MiniMax → generate commit message