feat(ci): 添加 OpenCodeReview PR 自动审查工作流

[zshs000]

• 本 PR 为项目引入了 OpenCodeReview (https://github.com/alibaba/open-code-review) 自动代码审查工具，用于在 PR 提交时自动进行代码审查并生成内联评论。支持 PR创建自动触发和评论手动触发（/open-code-review 或 @open-code-review）。

[gemini-code-assist]

Note

Gemini is unable to generate a review for this pull request due to the file types involved not being currently supported.

[github-actions]

🔍 OpenCodeReview found 3 issue(s) in this PR.

• ✅ 3 posted as inline comment(s)
• 📝 0 posted as summary (missing line info)

[github-actions]

🔍 OpenCodeReview found 5 issue(s) in this PR.

• ✅ 5 posted as inline comment(s)
• 📝 0 posted as summary (missing line info)

[github-actions]

🔍 OpenCodeReview found 10 issue(s) in this PR.

• ✅ 8 posted as inline comment(s)
• 📝 2 posted as summary (missing line info)

---

📄 .github/workflows/ocr-review.yml

安全风险：ocr review命令的输出直接写入文件并cat显示，如果OCR输出包含敏感信息，可能会在GitHub Actions日志中泄露。建议：1) 对输出文件进行加密或混淆处理；2) 或者只记录必要的错误信息，避免完整输出日志；3) 考虑使用::add-mask::来掩码敏感信息。

💡 Suggested Change

Before:

          # Run OCR in range mode with JSON output
          ocr review \
            --from "origin/${BASE_REF}" \
            --to "origin/${HEAD_REF}" \
            --format json \
            > /tmp/ocr-result.json 2>/tmp/ocr-stderr.log || true

          echo "OCR review completed. Output:"
          cat /tmp/ocr-result.json
          echo "OCR review completed. Error log:"
          cat /tmp/ocr-stderr.log

After:

          # Run OCR in range mode with JSON output
          ocr review \
            --from "origin/${BASE_REF}" \
            --to "origin/${HEAD_REF}" \
            --format json \
            > /tmp/ocr-result.json 2>/tmp/ocr-stderr.log || true

          echo "OCR review completed. Check /tmp/ocr-result.json for details."

---

📄 .github/workflows/ocr-review.yml

代码重复：formatComment和formatCommentMarkdown函数有重复的代码逻辑，特别是处理suggestion_code的部分。建议：1) 提取公共逻辑到辅助函数；2) 或者使用统一的格式化函数；3) 减少代码重复，提高可维护性。

💡 Suggested Change

Before:

            function formatComment(comment) {
              let body = comment.content || '';

              // Add code suggestion if available
              if (comment.suggestion_code && comment.existing_code) {
                body += '\n\n**Suggestion:**\n';
                body += '```suggestion\n';
                body += comment.suggestion_code;
                if (!comment.suggestion_code.endsWith('\n')) body += '\n';
                body += '```';
              }

              return body;
            }

            function formatCommentMarkdown(comment) {
              let md = `### 📄 \`${comment.path}\``;
              if (comment.start_line && comment.end_line) {
                md += ` (L${comment.start_line}-L${comment.end_line})`;
              }
              md += '\n\n';
              md += comment.content || '';

              if (comment.suggestion_code && comment.existing_code) {
                md += '\n\n<details><summary>💡 Suggested Change</summary>\n\n';
                md += '**Before:**\n```\n' + comment.existing_code + '\n```\n\n';
                md += '**After:**\n```\n' + comment.suggestion_code + '\n```\n\n';
                md += '</details>';
              }

              return md;
            }

After:

            function formatSuggestion(comment) {
              if (!comment.suggestion_code || !comment.existing_code) return '';
              
              let md = '\n\n<details><summary>💡 Suggested Change</summary>\n\n';
              md += '**Before:**\n```\n' + comment.existing_code + '\n```\n\n';
              md += '**After:**\n```\n' + comment.suggestion_code + '\n```\n\n';
              md += '</details>';
              return md;
            }

            function formatComment(comment) {
              let body = comment.content || '';

              // Add code suggestion if available
              if (comment.suggestion_code && comment.existing_code) {
                body += '\n\n**Suggestion:**\n';
                body += '```suggestion\n';
                body += comment.suggestion_code;
                if (!comment.suggestion_code.endsWith('\n')) body += '\n';
                body += '```';
              }

              return body;
            }

            function formatCommentMarkdown(comment) {
              let md = `### 📄 \`${comment.path}\``;
              if (comment.start_line && comment.end_line) {
                md += ` (L${comment.start_line}-L${comment.end_line})`;
              }
              md += '\n\n';
              md += comment.content || '';
              md += formatSuggestion(comment);

              return md;
            }

[zshs000]

实测效果可能不是很好，可能是因为模型使用了 MiMo2.5-Pro，但 opus 的渠道不太稳定，先用着吧。

同时这个技术对我来说还是挺新颖的，给了我一些思路。

目前主要存在两个问题：

1. 结果不一致：同一个 PR，代码没有修改，上一次没有给出意见，这次却给出了
2. 错误意见无法纠正：审查给出的错误意见没有反馈机制告诉它"这个判断是错的"，导致后续审查继续重复同样的错误建议。

[zshs000]

同时项目本身存在的审查体系已经能做到充分的审查了，所以这些只是兜底