feat(provider): add MiniMax M3 model and prune deprecated M2.x variants#3435
Closed
octo-patch wants to merge 1 commit into
Closed
feat(provider): add MiniMax M3 model and prune deprecated M2.x variants#3435octo-patch wants to merge 1 commit into
octo-patch wants to merge 1 commit into
Conversation
Add MiniMax-M3 as the new default model and remove the deprecated M2, M2.1, M2.1-highspeed, M2.5, and M2.5-highspeed entries. Keeps M2.7 and M2.7-highspeed as legacy options for users still on the previous generation.
|
octo-patch 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. |
Contributor
|
closing in favour of #3434 |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Updates the MiniMax provider model catalog in
crates/forge_repo/src/provider/provider.json:MiniMax-M3as the new top-of-list (default) entry — the latest generation MiniMax model with enhanced reasoning, function calling, and an extended (1M) context window.MiniMax-M2.7andMiniMax-M2.7-highspeedas legacy options for users still on the previous generation.MiniMax-M2,MiniMax-M2.1,MiniMax-M2.1-highspeed,MiniMax-M2.5,MiniMax-M2.5-highspeed. These are no longer recommended for new sessions; the M2.7 line covers the same use cases at parity or better quality.This follows the same minimal-edit pattern used for prior model catalog updates (e.g. #2727, #2701, #2597, #2557). Other knobs — base URL (
api.minimax.io),MINIMAX_API_KEYenv var, the OpenRouterSetMinimaxParamstransformer, and OpenCode model routing — are intentionally untouched.Why
MiniMax-M3is the current production model at MiniMax and outperforms the M2.x line on coding/agentic benchmarks. Surfacing it as the default lets new users pick it up automatically; pruning the older entries keeps the picker focused on the models that are still recommended.Changes
crates/forge_repo/src/provider/provider.json— only theid: "minimax"modelsarray is touched. 9 insertions / 49 deletions, all data-only (no schema changes).Test plan
cargo check -p forge_repopasses (data-only edit; existingProviderConfigschema is unchanged).cargo test -p forge_repo—test_load_provider_configsstill loads the catalog; no minimax-specific assertions exist that depend on the removed model IDs.forgelistsMiniMax-M3first under the MiniMax provider; selecting it routes through the existing Anthropic-compatible endpoint without code changes.