Fix/minimax context window and models

[Rexarrior]

• Add MiniMax-M2.7, MiniMax-M2.7-highspeed, MiniMax-M2.5-highspeed, MiniMax-M2.1-highspeed models
• Update contextWindow for MiniMax-M2 and MiniMax-M2.1 from 192000 to 204800
• Add pricing links and TokenPlan billing notes to model descriptions
• Add highspeed subscription note to -highspeed models
• Update tests for new models and corrected contextWindow values

Related GitHub Issue

Closes: #11999
Note; unfortunally, there is no way to get models list dynamically from the provider. So, i've skip changes, related to fix of this aspect.

Related Issues (Addressing Long-Standing Requests)

This PR also addresses several related MiniMax model requests that have been waiting for implementation:

• [BUG] The MiniMax-M2.7 model is missing #11981 - [BUG] The MiniMax-M2.7 model is missing from dropdown
• [ENHANCEMENT] Add MiniMax M2.7 to Minimax Provider #11953 - [ENHANCEMENT] Add MiniMax M2.7 to Minimax Provider
• [ENHANCEMENT] add model minimax -m2.5 #11457 - [ENHANCEMENT] add model minimax -m2.5

Roo Code Task Context (Optional)

Description

Adds the complete set of MiniMax M2 series models to the Roo Code provider:

• MiniMax-M2.7 - New model with 204,800 context window
• MiniMax-M2.7-highspeed - High-speed variant (100 tps vs 60 tps)
• MiniMax-M2.5-highspeed - High-speed variant of existing M2.5
• MiniMax-M2.1-highspeed - High-speed variant of existing M2.1

Also fixes incorrect context window values:

• MiniMax-M2: 192,000 → 204,800
• MiniMax-M2.1: 192,000 → 204,800

Updated model descriptions to include:

• Links to MiniMax pricing
• Note about TokenPlan billing: "When using TokenPlan, usage is billed per request, not per token."
• High-speed subscription requirements for -highspeed models

Test Procedure

• Unit tests pass: 30 MiniMax provider tests + 23 useSelectedModel tests
• Manual testing confirmed new models appear in model selector
• Verified context window values display correctly (204,800) for all M2 series models

Pre-Submission Checklist

• Issue Linked: This PR is linked to an approved GitHub Issue ([BUG] MiniMax provider, model m2.7 (when use as custom value ) - bad context length (extremly small) #11999).
• Scope: My changes are focused on the linked issue (one major feature/fix per PR).
• Self-Review: I have performed a thorough self-review of my code.
• Testing: New and/or updated tests have been added to cover my changes.
• Documentation Impact: No user-facing documentation updates required (model list is auto-generated).
• Contribution Guidelines: I have read and agree to the Contributor Guidelines.

Screenshots / Videos

Documentation Updates

• No documentation updates are required.

Additional Notes

Get in Touch

Diskord: rexarrior
telegram: t.me/rexarrior
email: rexarrior@yandex.ru

Interactively review PR in Roo Code Cloud

[hannesrudolph]

@roomote is this solid?

[roomote-v0]

Fixaroo   See task

Fixed the core issue from #11999: unknown/custom MiniMax model IDs are now passed through to the API instead of being silently replaced with the default, and the frontend falls back to default model info so context window no longer displays as 1. All tests and checks pass (31 backend + 24 frontend tests).

_{View commit | Revert commit}