feat(tenant): bill AI points by output characters

Previously AI point cost was computed from request (input) characters at
reservation time. Switch to reserving a single point up front and
settling the final cost from the generated output length on completion.

- Reserve 1 point (or FixedPoints) instead of pricing on request chars
- On completion, recompute points from output chars vs base chars,
  update the reservation amounts, and post a ledger delta for the
  top-up/refund; invalidate the workspace quota summary cache
- MarkCompleted now persists final request_chars/base_chars/points
- Use ceil division in calculateAIPointCost so an exact base boundary
  charges one point instead of rolling over
- Thread output text through all CompleteAIPoints callers (article
  selection, KOL assist, question expansion, template assist, compliance
  judge) and return the settled reservation
- Add unit tests plus an integration test gated on TEST_DATABASE_URL
- Update the user manual: billing is by output characters

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

user-manual/11-AI点数与套餐.md

@@ -26,7 +26,7 @@
 
 ### 计费基础
 
-- 每个 AI 调用按"请求字数 / 基准字数"换算成点数
+- 每个 AI 调用按"输出字数 / 基准字数"换算成点数
 - 套餐越高，**基准字数** 越大（同样请求消耗的点数越少）
 - 流水里能看到「{字数} 字 / 基准 {基准}」的换算说明
 
@@ -80,7 +80,7 @@ AI 任务在提交时会**先预占**对应点数，任务完成后才正式确
 
 - **使用场景**：哪类操作触发的扣点
 - **点数**：本次消耗（负数表示扣除，正数表示退回）
-- **计费字数**：实际请求字数
+- **计费字数**：实际输出字数
 - **创建时间**、**状态**
 
 如果有"莫名其妙的扣点"：