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/echo/fusion/route.ts

@@ -4,6 +4,7 @@ import { getChatProvider } from '@/lib/ai/factory'
 import { getSystemConfig } from '@/lib/config'
 import prisma from '@/lib/prisma'
 import { hasUserAiConsent } from '@/lib/consent/server-consent'
+import { withAiQuota, handleQuotaHttpError } from '@/lib/ai-quota'
 
 /**
  * POST /api/ai/echo/fusion
@@ -34,7 +35,6 @@ export async function POST(req: NextRequest) {
       )
     }
 
-    // Fetch the notes
     const notes = await prisma.note.findMany({
       where: {
         id: { in: noteIds },
@@ -55,11 +55,9 @@ export async function POST(req: NextRequest) {
       )
     }
 
-    // Get AI provider
     const config = await getSystemConfig()
     const provider = getChatProvider(config)
 
-    // Build fusion prompt
     const notesDescriptions = notes.map((note, index) => {
       return `Note ${index + 1}: "${note.title || 'Untitled'}"
 ${note.content}`
@@ -90,21 +88,21 @@ Output format:
 
 Begin:`
 
-    try {
-      const fusedContent = await provider.generateText(fusionPrompt)
-
-      return NextResponse.json({
-        fusedNote: fusedContent,
-        notesCount: notes.length
-      })
-    } catch (error) {
-      return NextResponse.json(
-        { error: 'Failed to generate fusion' },
-        { status: 500 }
-      )
-    }
+    const fusedContent = await withAiQuota(
+      session.user.id,
+      'reformulate',
+      () => provider.generateText(fusionPrompt),
+      { lane: 'chat' },
+    )
 
+    return NextResponse.json({
+      fusedNote: fusedContent,
+      notesCount: notes.length
+    })
   } catch (error) {
+    const quotaResp = handleQuotaHttpError(error)
+    if (quotaResp) return quotaResp
+    console.error('[/api/ai/echo/fusion] Error:', error)
     return NextResponse.json(
       { error: 'Failed to process fusion request' },
       { status: 500 }

memento-note/app/api/ai/echo/route.ts

@@ -2,6 +2,7 @@ import { NextRequest, NextResponse } from 'next/server'
 import { auth } from '@/auth'
 import { memoryEchoService } from '@/lib/ai/services/memory-echo.service'
 import { hasUserAiConsent } from '@/lib/consent/server-consent'
+import { reserveUsageOrThrow, QuotaExceededError } from '@/lib/entitlements'
 
 /**
  * GET /api/ai/echo
@@ -27,6 +28,7 @@ export async function GET(req: NextRequest) {
     }
 
     // Get next insight (respects frequency limits)
+    await reserveUsageOrThrow(session.user.id, 'reformulate')
     const insight = await memoryEchoService.getNextInsight(session.user.id)
 
     if (!insight) {
@@ -41,6 +43,9 @@ export async function GET(req: NextRequest) {
     return NextResponse.json({ insight })
 
   } catch (error) {
+    if (error instanceof QuotaExceededError) {
+      return NextResponse.json(error.toJSON(), { status: 429 })
+    }
     console.error('[/api/ai/echo] GET error:', error)
     return NextResponse.json(
       { error: 'Failed to fetch Memory Echo insight' },