Kimi K2.8 Preview rolls out across Kimi Code with three thinking levels and 1M context

What changed

Kimi has fully rolled out K2.8 Preview in Kimi Code while keeping the `kimi-for-coding` model ID, so existing clients and third-party integrations do not need a configuration change. The official release notes list low, high and max thinking-effort settings and up to a 1M-token context window across membership tiers; performance comparisons with K3 are publisher-reported evaluations.