feat: add MiniMax as a new LLM provider with M2.7 default

[octo-patch]

Summary

Add MiniMax as a first-class LLM provider for Continue, with the latest M2.7 model as default.

Changes

• Add MiniMax provider extending OpenAI with temperature clamping and response_format handling
• Add MiniMax-M2.7 and MiniMax-M2.7-highspeed as default models
• Include MiniMax-M2.5 and MiniMax-M2.5-highspeed as available alternatives
• Add GUI model selection with all MiniMax models
• Add documentation page at docs/customize/model-providers/more/minimax.mdx
• Register MiniMax in config-types, openai-adapters, and llm-info packages

Models

Model	Description
MiniMax-M2.7 (default)	Latest flagship model with enhanced reasoning and coding. 204K context.
MiniMax-M2.7-highspeed	High-speed version of M2.7 for low-latency scenarios. 204K context.
MiniMax-M2.5	Peak performance with ultimate value. 204K context.
MiniMax-M2.5-highspeed	Same performance as M2.5, faster and more agile. 204K context.

Why

MiniMax-M2.7 is the latest flagship model with enhanced reasoning and coding capabilities, available via an OpenAI-compatible API at https://api.minimax.io/v1.

Testing

• Integration tested with MiniMax API
• All model IDs verified against MiniMax platform

[github-actions]

Thank you for your submission, we really appreciate it. Like many open-source projects, we ask that you all sign our Contributor License Agreement before we can accept your contribution. You can sign the CLA by just posting a Pull Request Comment same as the below format.

---

I have read the CLA Document and I hereby sign the CLA

---

1 out of 2 committers have signed the CLA.
✅ (octo-patch)[https://github.com/octo-patch]
❌ @pr Bot
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 can retrigger this bot by commenting recheck in this Pull Request. Posted by the CLA Assistant Lite bot.}

[cubic-dev-ai]

1 issue found across 10 files

Prompt for AI agents (unresolved issues)

Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.


<file name="packages/openai-adapters/src/index.ts">

<violation number="1" location="packages/openai-adapters/src/index.ts:145">
P1: MiniMax is wired to generic `OpenAIApi`, which skips the repo’s MiniMax-specific request fixes (temperature clamping and `response_format` removal), creating a real incompatibility path in adapter-based runtime flows.</violation>
</file>

_{Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.}

[octo-patch]

I have read the CLA Document and I hereby sign the CLA

[RomneyDa]

@octo-patch thanks for the contribution, I think this provider should definitely be added.

Could you check a couple things?

• PROVIDER_SUPPORTS_IMAGES
• PROVIDER_HANDLES_TEMPLATING - I think yes for minimax
• PARALLEL_PROVIDERS

You can look up a provider string like "nebius" to see other places you might want to double check for minimax for completeness

[RomneyDa]

note CLA requirement!

[octo-patch]

Thanks for the review @RomneyDa! Great catch on the missing provider arrays. I've pushed a fix in c0b5501:

• PROVIDER_HANDLES_TEMPLATING — added ✅ (MiniMax uses OpenAI-compatible chat completions API, so it handles message formatting natively)
• PARALLEL_PROVIDERS — added ✅ (MiniMax supports parallel tool calls)
• PROVIDER_SUPPORTS_IMAGES — intentionally not added, since MiniMax M2.7 is text-only and does not support vision/image inputs

Regarding CLA — I signed it in my earlier comment above.

Let me know if anything else needs attention!