feat: add MiniMax provider catalog support - #1918
Open
octo-patch wants to merge 2 commits into
Open
Conversation
Contributor
Reviewer's Guide在模型提供者枚举中增加 MiniMax 作为受支持的提供者，通过兼容 OpenAI 的路径为 LLM 和 Embeddings 提供路由，允许在多模态工作流白名单中使用，并引入专门的 MiniMax catalog YAML，其中包含两个模型及其能力元数据。 通过 OpenAI 兼容路径进行 MiniMax 路由的序列图sequenceDiagram
actor User
participant BaseModels as get_provider_llm_class
participant EmbeddingsFactory as get_provider_embedding_class
User->>BaseModels: get_provider_llm_class(ModelProvider.MINIMAX)
BaseModels-->>User: CompatibleChatOpenAI
User->>EmbeddingsFactory: get_provider_embedding_class(ModelProvider.MINIMAX)
EmbeddingsFactory-->>User: OpenAIEmbeddings
File-Level Changes
Tips and commandsInteracting with Sourcery
Customizing Your Experience访问你的 dashboard 以：
Getting HelpOriginal review guide in EnglishReviewer's GuideAdds MiniMax as a supported provider across the model provider enum, OpenAI-compatible routing for LLMs and embeddings, multimodal workflow allowlist, and introduces a dedicated MiniMax catalog YAML with two models and capabilities metadata. Sequence diagram for MiniMax routing through OpenAI-compatible pathssequenceDiagram
actor User
participant BaseModels as get_provider_llm_class
participant EmbeddingsFactory as get_provider_embedding_class
User->>BaseModels: get_provider_llm_class(ModelProvider.MINIMAX)
BaseModels-->>User: CompatibleChatOpenAI
User->>EmbeddingsFactory: get_provider_embedding_class(ModelProvider.MINIMAX)
EmbeddingsFactory-->>User: OpenAIEmbeddings
File-Level Changes
Tips and commandsInteracting with Sourcery
Customizing Your ExperienceAccess your dashboard to:
Getting Help
|
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Hey - 我在这里给出了一些总体反馈：
- 在
minimax_models.yaml中，建议尽量复用现有的能力键（例如thinking），而不是引入thinking_only，除非能力的 schema 和下游逻辑已经明确支持这个新值。 - 请确认通过
CompatibleChatOpenAI和OpenAIEmbeddings来路由 MiniMax 时，是否与 MiniMax API 的语义（请求/响应字段、认证、速率限制）保持一致；如果存在任何差异，建议为 MiniMax 引入一个专门的、与提供方绑定的类。 - 由于 MiniMax 已被加入到支持多模态的 provider allowlist 中，请确保该 provider 下的非多模态模型（比如 MiniMax-M2.7）要么能通过能力进行过滤，要么能在工作流 UI/校验中得到合理的处理。
面向 AI 智能体的提示词
Please address the comments from this code review:
## Overall Comments
- In `minimax_models.yaml`, consider reusing existing capability keys (e.g., `thinking`) instead of introducing `thinking_only` unless the capability schema and downstream logic already explicitly support this new value.
- Confirm that routing MiniMax through `CompatibleChatOpenAI` and `OpenAIEmbeddings` matches the MiniMax API semantics (request/response fields, auth, rate limits), or introduce a dedicated provider-specific class if any divergences exist.
- Since MiniMax is added to the multimodal-compatible provider allowlist, ensure that non-multimodal models under this provider (like MiniMax-M2.7) are either filtered by capability or handled gracefully by the workflow UI/validation.帮我变得更有用！请在每条评论上点 👍 或 👎，我会根据你的反馈改进后续评审。
Original comment in English
Hey - I've left some high level feedback:
- In
minimax_models.yaml, consider reusing existing capability keys (e.g.,thinking) instead of introducingthinking_onlyunless the capability schema and downstream logic already explicitly support this new value. - Confirm that routing MiniMax through
CompatibleChatOpenAIandOpenAIEmbeddingsmatches the MiniMax API semantics (request/response fields, auth, rate limits), or introduce a dedicated provider-specific class if any divergences exist. - Since MiniMax is added to the multimodal-compatible provider allowlist, ensure that non-multimodal models under this provider (like MiniMax-M2.7) are either filtered by capability or handled gracefully by the workflow UI/validation.
Prompt for AI Agents
Please address the comments from this code review:
## Overall Comments
- In `minimax_models.yaml`, consider reusing existing capability keys (e.g., `thinking`) instead of introducing `thinking_only` unless the capability schema and downstream logic already explicitly support this new value.
- Confirm that routing MiniMax through `CompatibleChatOpenAI` and `OpenAIEmbeddings` matches the MiniMax API semantics (request/response fields, auth, rate limits), or introduce a dedicated provider-specific class if any divergences exist.
- Since MiniMax is added to the multimodal-compatible provider allowlist, ensure that non-multimodal models under this provider (like MiniMax-M2.7) are either filtered by capability or handled gracefully by the workflow UI/validation.Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.
Author
|
Updated the PR to keep MiniMax support scoped to the documented text models: MiniMax is no longer exposed as an embedding provider, and multimodal input now follows each model's declared capabilities so MiniMax-M2.7 remains text-only. I ran Python compile checks, focused catalog/source assertions, and git diff --check. |
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: Add MiniMax provider support to the model catalog and OpenAI-compatible runtime routing.
Changes:
Checks:
python -m compileallfor the patched Python modules.uv run pythonsource-level verification of the new provider enum, runtime routing, and catalog file.Summary by Sourcery
在模型目录和运行时路由中添加对 MiniMax 的支持。
新功能：
Original summary in English
Summary by Sourcery
Add MiniMax as a supported provider across the model catalog and runtime routing.
New Features: