Optimize AI system with batching, token tracking, and GDPR compliance

- Add AIUsageLog model for persistent token/cost tracking
- Implement batched processing for all AI services:
  - Assignment: 15 projects/batch
  - Filtering: 20 projects/batch
  - Award eligibility: 20 projects/batch
  - Mentor matching: 15 projects/batch
- Create unified error classification (ai-errors.ts)
- Enhance anonymization with comprehensive project data
- Add AI usage dashboard to Settings page
- Add usage stats endpoints to settings router
- Create AI system documentation (5 files)
- Create GDPR compliance documentation (2 files)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

src/components/settings/settings-content.tsx

@@ -19,6 +19,7 @@ import {
   Settings as SettingsIcon,
 } from 'lucide-react'
 import { AISettingsForm } from './ai-settings-form'
+import { AIUsageCard } from './ai-usage-card'
 import { BrandingSettingsForm } from './branding-settings-form'
 import { EmailSettingsForm } from './email-settings-form'
 import { StorageSettingsForm } from './storage-settings-form'
@@ -134,7 +135,7 @@ export function SettingsContent({ initialSettings }: SettingsContentProps) {
         </TabsTrigger>
       </TabsList>
 
-      <TabsContent value="ai">
+      <TabsContent value="ai" className="space-y-6">
         <Card>
           <CardHeader>
             <CardTitle>AI Configuration</CardTitle>
@@ -146,6 +147,7 @@ export function SettingsContent({ initialSettings }: SettingsContentProps) {
             <AISettingsForm settings={aiSettings} />
           </CardContent>
         </Card>
+        <AIUsageCard />
       </TabsContent>
 
       <TabsContent value="branding">