<feature>[ai]: add BareMetal2 runtime API surface

[MatheMatrix]

Summary

AIOS 5.5.32 BareMetal2 推理运行时的 zstack 控制面 API / schema / SDK 表面。这个 MR 只覆盖已落地的公开表面，不宣称整个特性可交付。

无对应 Jira Feature。与 premium / utility / ui-next 同名分支一起合并。

Locked decisions implemented here

• 预创建 BareMetal2 资源池；部署默认 Auto，Pinned 是可选硬约束
• 用户只选 GPU 规格和数量，不选具体卡
• 增加 placement / target / GPU inventory / runtime state 的 schema、SDK、ApiHelper 和错误码

Changes

• V5.5.32__schema.sql: BareMetal2 GPU inventory 与 model service runtime 字段
• SDK: DeployModelService / ModelService / ModelServiceInstanceInventory / BareMetal2ChassisGpuDeviceInventory
• ApiHelper.groovy 和 i18n error mapping

Testing

• 生成物 sdk / apihelper 已刷新
• 前序 143 模块 premium reactor 曾通过（历史证据，不冒充当前快照全绿）
• CI pipeline
• 真实 NVIDIA / vLLM / MetaX 实机

Not closed

• 多机数据面启动（业务 L3 / Ray process graph）
• 刷新产物后的浏览器 E2E
• NVIDIA + vLLM / MetaX 实机门禁

sync from gitlab !10733

[coderabbitai]

Warning

Review limit reached

You’ve reached a temporary PR review limit under our Fair Usage Limits Policy.

Your recent review volume is higher than typical usage, so adaptive limits are currently applied.

Next review available in: 28 minutes

Limit details: You’ve used all 1 included review currently available under your plan. You completed 86 included PR reviews in the past 7 days; at that activity level, included reviews refill at 1 review per hour.

Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available.
You're only billed for reviews past your plan's rate limits ($0.25/file).

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details

⚙️ Run configuration

Configuration used: Path: http://open.zstack.ai:20001/code-reviews/zstack-cloud.yaml (via .coderabbit.yaml)

Review profile: CHILL

Plan: Pro

Run ID: 5a102ee9-7314-4436-8b32-e167654ef15e

📥 Commits

Reviewing files that changed from the base of the PR and between 54032c3 and b24e1f1.

⛔ Files ignored due to path filters (9)

• conf/i18n/globalErrorCodeMapping/global-error-en_US.json is excluded by !**/*.json
• conf/i18n/globalErrorCodeMapping/global-error-zh_CN.json is excluded by !**/*.json
• sdk/src/main/java/org/zstack/sdk/BareMetal2ChassisGpuDeviceInventory.java is excluded by !sdk/**
• sdk/src/main/java/org/zstack/sdk/DeployAppDevelopmentServiceAction.java is excluded by !sdk/**
• sdk/src/main/java/org/zstack/sdk/DeployModelEvalServiceAction.java is excluded by !sdk/**
• sdk/src/main/java/org/zstack/sdk/DeployModelServiceAction.java is excluded by !sdk/**
• sdk/src/main/java/org/zstack/sdk/MatchModelServiceTemplateWithModelAction.java is excluded by !sdk/**
• sdk/src/main/java/org/zstack/sdk/ModelService.java is excluded by !sdk/**
• sdk/src/main/java/org/zstack/sdk/ModelServiceInstanceInventory.java is excluded by !sdk/**

📒 Files selected for processing (3)

• conf/db/upgrade/V5.5.32__schema.sql
• testlib/src/main/java/org/zstack/testlib/ApiHelper.groovy
• utils/src/main/java/org/zstack/utils/clouderrorcode/CloudOperationsErrorCode.java

---

_{Comment @coderabbitai help to get the list of available commands.}