fix(middlewares): 标题模型推理不再泄漏到 UI 流 + open/ephemeral 会话避免无谓 DB 访问

- title: 标题模型用隔离 config(不继承父级 streaming callbacks),force_disable_thinking,<think> 块清洗,避免推理 token 进入实时流/运行日志
- uploads: 无文件的普通对话轮次直接跳过,不再解析线程归属(避免命中 DB)
- thread_data: ephemeral 会话用当前登录用户解析数据目录
- thread_paths: open-/__skill-review__ 等合成线程视为 local-only,直接用当前用户
- frontend: 新增 build:test 构建脚本

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

frontend-web/package.json

@@ -7,6 +7,7 @@
     "dev": "vite",
     "build": "node --max-old-space-size=8192 ./node_modules/vite/bin/vite.js build",
     "build:sit": "node --max-old-space-size=8192 ./node_modules/vite/bin/vite.js build --mode sit",
+    "build:test": "node --max-old-space-size=8192 ./node_modules/vite/bin/vite.js build --mode test",
     "build:network": "node --max-old-space-size=8192 ./node_modules/vite/bin/vite.js build --mode network",
     "preview": "vite preview",
     "typecheck": "tsc --noEmit"