fix(quotas): unifier le décompte IA (BYOK, rollback) et combler les fuites

Centralise la réserve via ai-quota, corrige admin unavailable (-1), brancher les routes sans quota et le host-pays brainstorm, avec usage-meter élargi, noms de clusters, MCP et ajustements dashboard/insights.

Co-authored-by: Cursor <cursoragent@cursor.com>

memento-note/app/api/ai/search-overview/route.ts

@@ -1,7 +1,7 @@
-import { rateLimit } from '@/lib/rate-limit'
 import { NextRequest, NextResponse } from 'next/server'
 import { auth } from '@/auth'
 import { searchOverviewService } from '@/lib/ai/services/search-overview.service'
+import { withAiQuota, handleQuotaHttpError } from '@/lib/ai-quota'
 
 export async function POST(request: NextRequest) {
   try {
@@ -15,11 +15,19 @@ export async function POST(request: NextRequest) {
       return NextResponse.json({ error: 'query and results required' }, { status: 400 })
     }
 
-    const overview = await searchOverviewService.generate(query, results, language)
+    const overview = await withAiQuota(
+      session.user.id,
+      'semantic_search',
+      () => searchOverviewService.generate(query, results, language),
+      { lane: 'chat' },
+    )
 
     return NextResponse.json(overview)
-  } catch (error: any) {
+  } catch (error: unknown) {
+    const quotaResp = handleQuotaHttpError(error)
+    if (quotaResp) return quotaResp
     console.error('[Search Overview] Error:', error)
-    return NextResponse.json({ error: error.message, hasRelevantInfo: false, answer: '' }, { status: 500 })
+    const message = error instanceof Error ? error.message : 'Search overview failed'
+    return NextResponse.json({ error: message, hasRelevantInfo: false, answer: '' }, { status: 500 })
   }
 }