feat(server): meter AI point usage across tenant AI features

Adds an ai_point_usage_logs ledger and a reserve/refund/complete pipeline
that charges AI points for article selection optimize, template analyze
/title/outline, and KOL prompt generate/optimize. Pending reservations
are reconciled when the kol-assist worker and template-assist tasks
finish or fail, so points refund automatically on errors. Workspace now
exposes the AI quota status and a paginated usage ledger.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

server/internal/tenant/transport/article_handler.go

@@ -48,7 +48,7 @@ func NewArticleHandler(a *bootstrap.App) *ArticleHandler {
 			a.DB,
 			a.LLM,
 			a.Config.LLM.MaxOutputTokens,
-		),
+		).WithCache(a.Cache),
 		promptGenerateSvc: app.NewPromptRuleGenerationService(
 			a.DB,
 			a.LLM,
@@ -344,7 +344,7 @@ func (h *ArticleHandler) OptimizeSelectionStream(c *gin.Context) {
 	var streamed strings.Builder
 	var streamWriteErr error
 
-	result, err := h.selectionOptimize.OptimizeSelection(streamCtx, req, func(delta string) {
+	result, err := h.selectionOptimize.OptimizeSelection(streamCtx, id, req, func(delta string) {
 		if delta == "" || streamWriteErr != nil {
 			return
 		}