feat: upgrade MiniMax default model to M3 (keep M2.7)#91
Open
octo-patch wants to merge 3 commits into
Open
Conversation
Add MiniMax M2.5 and M2.5-highspeed as pre-configured LLM provider clients using BAML's OpenAI-compatible provider with custom base_url. MiniMax offers a 204K context window and an OpenAI-compatible API. Changes: - Add MiniMaxM25 and MiniMaxM25Highspeed client definitions in clients.baml (template and workshop final) - Include MiniMax in round-robin (CustomFast) and fallback (OpenaiFallback) strategies - Add BAML test cases for MiniMax provider - Add unit tests (14 tests) validating BAML configuration - Add integration tests (5 tests) verifying MiniMax API compatibility - Update README with MiniMax setup instructions and env var
|
PR Bot seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account. You have signed the CLA already but the status is still pending? Let us recheck it. |
Add MiniMax-M2.7 and MiniMax-M2.7-highspeed as the latest recommended models, replacing M2.5 as the default in round-robin and fallback strategies. M2.5 clients remain available for backward compatibility. - Add MiniMaxM27 and MiniMaxM27Highspeed BAML client definitions - Update CustomFast round-robin and OpenaiFallback to use M2.7 - Add 9 unit tests and 5 integration tests for M2.7 models - Update README with M2.7 client documentation
octo-patch
changed the title
- Add MiniMax-M3 to model list and set as default - Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed - Remove older models (M2.5/M2.5-highspeed) - Update related tests
octo-patch
changed the title
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
2 participants
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 MiniMax BAML provider clients to use MiniMax-M3 as the default model.
MINIMAX_API_KEYandhttps://api.minimax.io/v1Changes (6 files)
packages/create-12-factor-agent/template/baml_src/clients.baml— AddMiniMaxM3client (placed first as default), keepMiniMaxM27/MiniMaxM27Highspeed, removeMiniMaxM25/MiniMaxM25Highspeed, updateOpenaiFallbackto useMiniMaxM3workshops/2025-05/final/baml_src/clients.baml— Same updates for the workshop templatepackages/create-12-factor-agent/template/test/minimax-provider.test.ts— 23 unit tests validating M3/M2.7 client config + assertions that M2.5/M2.1/M2/M1 are removedpackages/create-12-factor-agent/template/test/minimax-integration.test.ts— Live API tests for M3, M2.7, M2.7-highspeedpackages/create-12-factor-agent/template/baml_src/agent.baml— Update test comment from M2.5 to M3packages/create-12-factor-agent/template/README.md— Document M3 as default client, list M2.7 alternativesTest plan
npx tsx test/minimax-provider.test.ts)