Problem (one or two sentences)

Request to add Kimi K2 thinking to Google VertexAI provider

Context (who is affected and when)

.

Desired behavior (conceptual, not technical)

.

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)

Add new model moonshotai/kimi-k2-thinking-maas in packages/types/src/providers/vertex.ts with following configuration

{
	maxTokens: 262_144,
	contextWindow: 262_144,
	supportsPromptCache: false,
	supportsImages: false,
	inputPrice: 0.6,
	outputPrice: 2.5,
	description: "Kimi K2 Thinking Model with 256K context window.",
}

Trade-offs / risks (optional)

No response