feat(minimax): expose global OpenAI-compatible endpoint and M3 vision capability - #614
Open
octo-patch wants to merge 1 commit into
Open
Conversation
… capability Add the global api.minimax.io/v1 OpenAI-compatible endpoint alongside the existing China api.minimaxi.com/v1 endpoint as baseUrlOptions (China stays the default baseUrl). MiniMax-M3 accepts text/image/video input, so mark supports_vision=true on M3 and supports_vision=false on the text-only M2.7. The preset data source and regenerated builtin_presets fixture are kept in sync, and the preset test anchors the new endpoint and capability metadata.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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: parameter-refresh — MiniMax preset exposes only the China OpenAI-compatible endpoint and lacks explicit M3 input-capability metadata.
Changes
https://api.minimax.io/v1to the MiniMax builtin presetbaseUrlOptions, alongside the existing China endpointhttps://api.minimaxi.com/v1(China stays the defaultbaseUrl).supports_vision: trueonMiniMax-M3(accepts text/image/video input) andsupports_vision: falseon the text-onlyMiniMax-M2.7inmodelCapabilities, so the adapter's vision gate routes image input correctly per model.builtin_presets.jsonfixture from the updated preset source so the byte-identical round-trip contract stays green.Checks
cargo fmt --all -- --checkcargo run -p xtask --release -- gen-fixtures+git diff --exit-code -- tests/replay/fixtures/registry/cargo test -p codex-app-transfer-registry(lib + integration / golden round-trip)cargo test -p codex-app-transfer-adapters --lib(vision + MiniMax sanitize/M3 suites)The adapter already supports an Anthropic-compatible path via
anthropic_messagesand an M3 thinking wire (thinking:{type:disabled|adaptive}), so no routing change is required; this change only refreshes the preset's endpoint and capability metadata.