[ENHANCEMENT] Add support for GML-5-turbo model

[bikramswain1992]

Problem (one or two sentences)

Z.ai currently support glm-5-turbo model which is not present in Roo.

Context (who is affected and when)

All users who have Z.ai API and Coding plan subscriptions are not able to use glm-5-turbo model in Roo.

Desired behavior (conceptual, not technical)

"glm-5-turbo" is not available in the list of models for API provider Z.ai

Constraints / preferences (optional)

No response

Request checklist

• I've searched existing Issues and Discussions for duplicates
• This describes a specific problem with clear context and impact

Roo Code Task Links (optional)

No response

Acceptance criteria (optional)

No response

Proposed approach (optional)

No response

Trade-offs / risks (optional)

No response

I've analyzed this issue and here's my proposed implementation plan:

The Z.ai model definitions live in packages/types/src/providers/zai.ts. There are two model lists -- internationalZAiModels (for international API lines) and mainlandZAiModels (for China API lines). Currently glm-5 exists in both lists but glm-5-turbo does not.

Plan:

1. Add "glm-5-turbo" entry to internationalZAiModels in packages/types/src/providers/zai.ts with appropriate specs (context window, pricing, reasoning support, etc. -- modeled after glm-5 but adjusted for turbo variant characteristics if pricing/spec info is available from Z.ai docs)
2. Add "glm-5-turbo" entry to mainlandZAiModels in the same file with mainland-specific pricing
3. Update any existing tests in src/api/providers/__tests__/zai.spec.ts if needed to cover the new model

Question before proceeding:

• Could you confirm the specs (context window, max output tokens, pricing) for glm-5-turbo? If not available, I can use the same specs as glm-5 as a starting point and they can be refined later.

Please mention @roomote in a comment saying that you approve this plan, and I'll proceed with the implementation.

[bikramswain1992]

Pricing: $1.2 per million input token, $ 0.24 per million cached input token, $ 4.0 per million output token
Context window: 200,000
Max output token: 128, 000

@roomote I approve this plan

Thanks for the specs! I'll proceed with adding glm-5-turbo to both international and mainland Z.ai model lists with the provided pricing and context window details. Will open a PR shortly.

Opened a draft PR with my attempt at adding glm-5-turbo: #12022. Feedback welcome!