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/lib/ai/services/agent-suggestion.service.ts

@@ -10,6 +10,7 @@ import { clusteringService } from './clustering.service'
 import { getChatProvider } from '@/lib/ai/factory'
 import { getSystemConfig } from '@/lib/config'
 import { calculateNextRun } from '@/lib/agents/schedule'
+import { withAiQuota } from '@/lib/ai-quota'
 
 const MIN_CLUSTER_NOTES = 3
 const MAX_SUGGESTIONS_PER_RUN = 3
@@ -51,6 +52,7 @@ function clusterCoveredByAgent(
 }
 
 async function buildSuggestionWithLlm(
+  userId: string,
   topic: string,
   noteTitles: string[],
   noteCount: number,
@@ -63,10 +65,6 @@ async function buildSuggestionWithLlm(
   }
 
   try {
-    const config = await getSystemConfig()
-    const provider = getChatProvider(config)
-    if (!provider) return fallback
-
     const prompt = `Tu proposes un agent IA pour un second cerveau (prise de notes).
 Thème détecté: "${topic}"
 Notes liées (titres): ${noteTitles.slice(0, 5).join(' | ') || 'sans titre'}
@@ -75,7 +73,14 @@ Nombre de notes: ${noteCount}
 Retourne UNIQUEMENT du JSON valide:
 {"reason":"1 phrase pourquoi un agent est utile","suggestedRole":"prompt système de l'agent (2-3 phrases, français)","suggestedType":"researcher|monitor","suggestedFrequency":"daily|weekly"}`
 
-    const raw = await provider.generateText(prompt)
+    const raw = await withAiQuota(userId, 'reformulate', async () => {
+      const config = await getSystemConfig()
+      const provider = getChatProvider(config)
+      if (!provider) return null
+      return provider.generateText(prompt)
+    }, { lane: 'chat' })
+
+    if (!raw) return fallback
     const match = raw.match(/\{[\s\S]*\}/)
     if (!match) return fallback
     const parsed = JSON.parse(match[0])
@@ -122,6 +127,7 @@ export class AgentSuggestionService {
         select: { title: true },
       })
       const llm = await buildSuggestionWithLlm(
+        userId,
         topic,
         notes.map(n => n.title || 'Sans titre'),
         cluster.noteIds.length,