Add MiniMax-M3 and make it the default model for the MiniMax provider#301
Open
octo-patch wants to merge 1 commit into
Open
Add MiniMax-M3 and make it the default model for the MiniMax provider#301octo-patch wants to merge 1 commit into
octo-patch wants to merge 1 commit into
Conversation
Adds the new flagship model MiniMax-M3 to the MiniMax provider's static model list and promotes it to the default model hint. Keeps M2.7 and M2.7-highspeed for users who still want them; drops the older M2.5/M2.5-highspeed/M2.1/M2.1-highspeed/M2 entries from the static catalog so the picker leads with the current generation. Updates accompanying docs (OAUTH.md), the live-test target model, and the static-model regression assertion to match the new list. Co-Authored-By: Octopus <liyuan851277048@icloud.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
MiniMax's flagship text model is now MiniMax-M3. This PR pulls it into the
minimaxprovider preset so users pickingjcode login --provider minimaxland on the current generation by default.Changes
crates/jcode-provider-metadata/src/catalog.rs: bumpMINIMAX_PROFILE.default_modelfromMiniMax-M2.7toMiniMax-M3.crates/jcode-base/src/provider_catalog.rs: rebuild the static model fallback for theminimaxprofile to exposeMiniMax-M3,MiniMax-M2.7, andMiniMax-M2.7-highspeed. Drop the olderM2.5 / M2.5-highspeed / M2.1 / M2.1-highspeed / M2entries; live/v1/modelswill still surface anything else the user's account has.crates/jcode-base/src/provider/openrouter_tests.rs: update the static-fallback regression to assert M3 is exposed (and replace the M2 assertion with the M3 one).crates/jcode-base/src/live_tests.rs: switch theminimaxlive-test target model from M2.7 to M3.OAUTH.md: refresh the default model hint in the MiniMax preset section.Only the
minimaxprovider's own list and default change; the other aggregators (opencode,cortecs,302ai,alibaba-coding-plan) that mention older MiniMax model IDs in their static catalogs are left alone, since those reflect what each upstream actually exposes.API base URL, env-file layout, China endpoint resolution, and the existing
MiniMax-M2.7-highspeedentry are all untouched.Notes
cargo test -p jcode-basesuite locally because of build resource limits on the machine I have access to. The metadata crate (cargo check -p jcode-provider-metadata) builds clean. All edits are mechanical model-ID string replacements; the test changes line up 1:1 with the new static list.Test plan
cargo test -p jcode-provider-metadatacargo test -p jcode-base provider_catalogcargo test -p jcode-base openrouterjcode login --provider minimax, confirm picker leads withMiniMax-M3and thatM2.7/M2.7-highspeedare still reachable.