<fix>[compute]: skip VmAttachNicOnHypervisorFlow when VM is stopped

[zstack-robot-1]

Resolves: ZSTAC-76466

Target: 5.5.6

sync from gitlab !9185

[coderabbitai]

概览

本次拉取请求引入了一份新的中文文档 CLAUDE.md，用于模块导航和开发指南，同时修改了 VmInstanceBase.java 中 NIC 挂载流程，使虚拟机仅在运行状态时才执行超级管理程序层的 NIC 挂接操作。

变更内容

集群 / 文件	摘要
文档新增 CLAUDE.md	新增中文文档，包含模块关键词查表、跨模块依赖关系、模块完整索引、Agent 搜索策略、构建约定与调试流程等内容。纯文档性内容，无代码实现变更。
虚拟机 NIC 挂接流程优化 compute/src/main/java/org/zstack/compute/vm/VmInstanceBase.java	修改 NIC 挂接流程的控制逻辑，VmAttachNicOnHypervisorFlow 步骤现仅在虚拟机处于运行状态时执行，避免对非活跃虚拟机进行不必要的超级管理程序级别操作。

代码审查工作量估计

🎯 1 (简单) | ⏱️ ~8 分钟

兔兔的庆贺诗

🐰 文档妙笔绘地图，模块路径一目清，
NIC 流程添逻辑，只在奔跑时挂接，
条件判别护虚机，代码优雅又贴心！ ✨

🚥 Pre-merge checks | ✅ 3 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (3 passed)

Check name	Status	Explanation
Title check	✅ Passed	标题遵循了规定的 [scope]: 格式，67个字符在72字符限制内，准确描述了主要变更内容。
Description check	✅ Passed	描述与变更集相关，包含 JIRA 工单号、目标分支和来源信息，虽然简洁但足够说明 PR 的目的。
Merge Conflict Detection	✅ Passed	✅ No merge conflicts detected when merging into 5.5.6

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing touches

• 📝 Generate docstrings

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment
• Commit unit tests in branch sync/ye.zou/fix/ZSTAC-76466

Warning

There were issues while running some tools. Please review the errors and either fix the tool's configuration or disable the tool if it's a critical failure.

🔧 ast-grep (0.40.5)

compute/src/main/java/org/zstack/compute/vm/VmInstanceBase.java

---

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

[coderabbitai]

Actionable comments posted: 2

🤖 Fix all issues with AI agents

In `@CLAUDE.md`:
- Around line 1-185: The file CLAUDE.md contains Chinese-only content which
violates the repository's all-files English policy; rename the file to
CLAUDE_zh_cn.md to apply the established Chinese-file exemption, and add an
English counterpart (CLAUDE.md) with equivalent content if the document must
remain in the repo for non-Chinese readers; update any references to CLAUDE.md
in docs/README or links to point to CLAUDE_zh_cn.md (or to the new English
CLAUDE.md) so nothing breaks.
- Line 22: Replace all Chinese text in CLAUDE.md with English equivalents:
specifically change the table entry "(ZBS 存储驱动)" to "(ZBS storage driver)"
(current line showing "| ZBS, MDS | `plugin/zbs/` | (ZBS 存储驱动) |"), change
"数据保护, 快照" to "data protection, snapshot" and "计费" to "billing", change "vhost
重连管理" to "vhost reconnection management", and replace "CBD 块存储", "Expon 存储",
"Xinfini 存储" with "CBD block storage", "Expon storage", "Xinfini storage"
respectively; then scan the rest of CLAUDE.md for other Chinese table cells,
headings (e.g., "跨模块依赖", "Premium 插件") and inline descriptions and convert them
to concise English equivalents throughout the document to ensure no Chinese
remains.

[coderabbitai]

⚠️ Potential issue | 🟠 Major

文件包含中文内容，违反编码规范

根据编码规范，所有文件（包括注释和文档）都应当使用正确的、无拼写错误的英文编写。当前文件 CLAUDE.md 完全使用中文编写。

尽管这是一个文档文件而非源代码，编码规范的模式 **/*.* 技术上匹配所有文件。根据历史学习记录，以 _zh_cn 结尾的文件可以豁免该规则，因为它们是为中文用户自动生成的本地化文件。

建议的解决方案：

1. 首选方案：将文件重命名为 CLAUDE_zh_cn.md 以符合中文文档的命名约定并获得自动豁免
2. 备选方案：如果此文档需要供中文开发者使用，请与团队确认是否可以为此类内部文档文件添加明确的编码规范豁免
3. 长期方案：创建英文版本 CLAUDE.md 和中文版本 CLAUDE_zh_cn.md

根据编码规范："代码里不应当有有中文，包括报错、注释等都应当使用正确的、无拼写错误的英文来写"

🤖 Prompt for AI Agents

In `@CLAUDE.md` around lines 1 - 185, The file CLAUDE.md contains Chinese-only
content which violates the repository's all-files English policy; rename the
file to CLAUDE_zh_cn.md to apply the established Chinese-file exemption, and add
an English counterpart (CLAUDE.md) with equivalent content if the document must
remain in the repo for non-Chinese readers; update any references to CLAUDE.md
in docs/README or links to point to CLAUDE_zh_cn.md (or to the new English
CLAUDE.md) so nothing breaks.

[coderabbitai]

⚠️ Potential issue | 🔴 Critical

🧩 Analysis chain

🏁 Script executed:

find . -name "CLAUDE.md" -type f

Repository: MatheMatrix/zstack

Length of output: 73

---

🏁 Script executed:

cat -n CLAUDE.md | sed -n '15,30p; 40,55p; 100,120p; 108,120p'

Repository: MatheMatrix/zstack

Length of output: 4312

---

将所有中文文本替换为正确的英文

根据编码规范，代码和文档中不应出现中文，包括注释和描述信息。CLAUDE.md 文件中包含大量中文文本，需要全部替换为英文：

• 第22行：(ZBS 存储驱动) → 应改为英文描述，如 (ZBS storage driver)
• 第46-47行：数据保护, 快照 和 计费 → 应改为 data protection, snapshot 和 billing
• 第106行：vhost 重连管理 → 应改为 vhost reconnection management
• 第113-115行：CBD 块存储、Expon 存储、Xinfini 存储 → 应改为 CBD block storage、Expon storage、Xinfini storage

此外，整个文档中还有大量其他中文文本（包括表格描述、章节标题如"跨模块依赖"、"Premium 插件"等），都需要替换为英文。

🤖 Prompt for AI Agents

In `@CLAUDE.md` at line 22, Replace all Chinese text in CLAUDE.md with English
equivalents: specifically change the table entry "(ZBS 存储驱动)" to "(ZBS storage
driver)" (current line showing "| ZBS, MDS | `plugin/zbs/` | (ZBS 存储驱动) |"),
change "数据保护, 快照" to "data protection, snapshot" and "计费" to "billing", change
"vhost 重连管理" to "vhost reconnection management", and replace "CBD 块存储", "Expon
存储", "Xinfini 存储" with "CBD block storage", "Expon storage", "Xinfini storage"
respectively; then scan the rest of CLAUDE.md for other Chinese table cells,
headings (e.g., "跨模块依赖", "Premium 插件") and inline descriptions and convert them
to concise English equivalents throughout the document to ensure no Chinese
remains.