feat: 统一图片 base64 读取入口并清理图像读取路径

[ThaddeusJiang]

变更内容

• 在 Vmemo.Memo.Image 新增 read_storage_base64 action 与 code_interface，统一从存储读取 base64 与 MIME 类型。
• Vmemo.Chat.AiRouter 改为通过 Image.read_storage_base64/2 读取图像数据，移除对 Vmemo.Ai.ImageData 的依赖。
• 删除不再使用的 lib/vmemo/ai/image_data.ex。
• 调整相关测试（caption/chat scoped/API）以匹配新的读取路径与测试约束。
• 补充 AGENTS 与 Elixir coding guide 中与 Ash 资源调用相关的约定。

验证

• 已完成分支提交与推送
• 本次未额外运行测试

[codecov]

Codecov Report

❌ Patch coverage is 54.54545% with 5 lines in your changes missing coverage. Please review.
✅ Project coverage is 39.84%. Comparing base (d9b4759) to head (47dc16e).
⚠️ Report is 2 commits behind head on main.

Files with missing lines	Patch %	Lines
lib/vmemo/memo/image.ex	50.00%	5 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #204      +/-   ##
==========================================
- Coverage   40.12%   39.84%   -0.28%     
==========================================
  Files         123      122       -1     
  Lines        6136     6103      -33     
==========================================
- Hits         2462     2432      -30     
+ Misses       3674     3671       -3     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.