docs: add technical report for codex handoff (2026-06-13)

refactor: deprecate llama-omni-server, use llama-server built-in omni endpoints

modal/omni: PRODUCTION DEPLOY - text inference fully verified, llama-server running on T4

modal/omni: text inference verified (Chinese OK, English needs fix)

modal/omni: llama-server inference verified on T4

docs: add production script protect warnings to deploy guide

docs: comprehensive Modal deploy guide (both solutions + pitfalls)

deploy_omni: llFile llama.cpp-omni compile succeeds on Modal T4

[PregoPal] 2026-06-11 全双工语音对话开发阶段完成

docs: 更新开发日志和本地部署经验，记录全双工实现细节

用户手动备份

技术路径

用户手动整理文件，并备份deploy_backup.py文件

docs: 部署成功报告 + 清理神秘文件 c

docs: 补充两种方案对比(wheel vs 源码编译)，明确预编译wheel仍属llama.cpp

docs: 技术日志-解释为什么预编译wheel部署这么快

docs: pre-refactor backup - before tech log integration

refactor: 合并三天总结到营养报告，移除独立Tab

docs: 新增项目架构说明书，包含完整模块分析、数据文件状态、协作规范与待办事项

docs: 更新部署日志 - Modal修复记录+API设计

docs: 更新开发日志 - 添加 deploy.py 已知问题4项 + 编译状态

docs: 更新部署经验文档和gitignore - 添加部署状态/API URL/清理规则

feat(modal): 部署 MiniCPM-o 4.5 到 Modal (llama.cpp + FastAPI)

docs: update 开发日志 with UI redesign iterations

feat: llama.cpp deploys MiniCPM-o 4.5 on Modal - technical report and client API

chore: save current version before UI improvements (i18n + font fix)

CLine 界面初版