在 conversations 表增加 playground_conversation_judge_json,流式/非流式对话评审结束后写入最近一次快照(整体分、逐轮分、对比文案、错误与基线文件名等)。新增只读 GET 供前端按会话拉取;评测台 Playground 切换会话时自动恢复,并提示基线是否和当时一致。
- Extend evaluation API: schemas, router, repo, admin and execution services - Improve user export markdown importer; add fixtures and importer tests - Session catalog repo/service updates; internal app wiring and docs - Add internal-eval.sh helper; refresh app-eval-web (App, styles, Vite)