feat(reply-quality): 👎 keeps a snapshot of the turn; admin 对话质量记录

A 👎 now saves, server side, the rated turn plus the context window the
model read for it (reconstructed from the stored session with the same
consultationHistoryWindow the consult route uses), model and run facts.
👍 is only counted. Switching to 👍 or clearing deletes the snapshot.
Bodies are blanked after 90 days; the row cascades on session delete
and on account deletion.

- Optional 不满意原因 panel under the answer after a 👎 (five reasons,
  200-char note, "会把这一轮对话发给我们排查").
- Admin 对话质量记录: 👍/👎 stats by day and model, list without text,
  audited snapshot open, 处理状态 + note (support.quality.read/write).
- Privacy draft: what a 👎 keeps, why, 90 days, deletion.
- Migration 20260930050000 is add-only; set_reply_rating() replaced with
  the same signature.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE

CONTEXT.md

@@ -29,7 +29,7 @@ _避免使用_：正常回复、可评价回复
 _避免使用_：原始异常、完整日志
 
 **故障上下文快照**：
-为排查 Agent 执行故障而保留的故障轮次及该次执行实际使用的近期上下文，不等同于完整会话副本。
+为排查 Agent 执行故障而保留的故障轮次及该次执行实际使用的近期上下文，不等同于完整会话副本。负向回复评价也保留一份：该轮提问与回答、按会话重建的模型上下文窗口与运行事实，90 天后清空正文。
 _避免使用_：完整聊天记录、错误消息
 
 **回复评价**：