fix: Restore all files lost during destructive rebase

A previous `git pull --rebase origin main` dropped 177 local commits,
losing 3400+ files across admin-v2, backend, studio-v2, website,
klausur-service, and many other services. The partial restore attempt
(660295e2) only recovered some files.

This commit restores all missing files from pre-rebase ref 98933f5e
while preserving post-rebase additions (night-scheduler, night-mode UI,
NightModeWidget dashboard integration).

Restored features include:
- AI Module Sidebar (FAB), OCR Labeling, OCR Compare
- GPU Dashboard, RAG Pipeline, Magic Help
- Klausur-Korrektur (8 files), Abitur-Archiv (5+ files)
- Companion, Zeugnisse-Crawler, Screen Flow
- Full backend, studio-v2, website, klausur-service
- All compliance SDKs, agent-core, voice-service
- CI/CD configs, documentation, scripts

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

admin-v2/app/(admin)/ai/llm-compare/page.tsx

@@ -12,6 +12,7 @@
 
 import { useState, useEffect, useCallback } from 'react'
 import { PagePurpose } from '@/components/common/PagePurpose'
+import { AIToolsSidebarResponsive } from '@/components/ai/AIToolsSidebar'
 
 interface LLMResponse {
   provider: string
@@ -210,21 +211,24 @@ export default function LLMComparePage() {
       {/* Page Purpose */}
       <PagePurpose
         title="LLM Vergleich"
-        purpose="Vergleichen Sie Antworten verschiedener KI-Provider (OpenAI, Claude, Self-hosted) fuer Qualitaetssicherung. Optimieren Sie Parameter und System Prompts fuer beste Ergebnisse."
+        purpose="Vergleichen Sie Antworten verschiedener KI-Provider (OpenAI, Claude, Self-hosted) fuer Qualitaetssicherung. Optimieren Sie Parameter und System Prompts fuer beste Ergebnisse. Standalone-Werkzeug ohne direkten Datenfluss zur KI-Pipeline."
         audience={['Entwickler', 'Data Scientists', 'QA']}
         architecture={{
           services: ['llm-gateway (Python)', 'Ollama', 'OpenAI API', 'Claude API'],
           databases: ['PostgreSQL (History)', 'Qdrant (RAG)'],
         }}
         relatedPages={[
-          { name: 'RAG Management', href: '/ai/rag', description: 'Training Data verwalten' },
-          { name: 'GPU Infrastruktur', href: '/infrastructure/gpu', description: 'GPU-Ressourcen' },
-          { name: 'OCR-Labeling', href: '/ai/ocr-labeling', description: 'Handschrift-Training' },
+          { name: 'Test Quality (BQAS)', href: '/ai/test-quality', description: 'Golden Suite & Synthetic Tests' },
+          { name: 'GPU Infrastruktur', href: '/ai/gpu', description: 'GPU-Ressourcen verwalten' },
+          { name: 'Agent Management', href: '/ai/agents', description: 'Multi-Agent System' },
         ]}
         collapsible={true}
         defaultCollapsed={true}
       />
 
+      {/* KI-Werkzeuge Sidebar */}
+      <AIToolsSidebarResponsive currentTool="llm-compare" />
+
       <div className="grid grid-cols-1 lg:grid-cols-3 gap-6">
         {/* Left Column: Input & Settings */}
         <div className="lg:col-span-1 space-y-4">