[split-required] Split website + studio-v2 monoliths (Phase 3 continued)

Website (14 monoliths split):
- compliance/page.tsx (1,519 → 9), docs/audit (1,262 → 20)
- quality (1,231 → 16), alerts (1,203 → 10), docs (1,202 → 11)
- i18n.ts (1,173 → 8 language files)
- unity-bridge (1,094 → 12), backlog (1,087 → 6)
- training (1,066 → 8), rag (1,063 → 8)
- Deleted index_original.ts (4,899 LOC dead backup)

Studio-v2 (5 monoliths split):
- meet/page.tsx (1,481 → 9), messages (1,166 → 9)
- AlertsB2BContext.tsx (1,165 → 5 modules)
- alerts-b2b/page.tsx (1,019 → 6), korrektur/archiv (1,001 → 6)

All existing imports preserved. Zero new TypeScript errors.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

website/app/admin/quality/_components/OverviewTab.tsx

@@ -0,0 +1,94 @@
+import { BQASMetrics, TrendData, TestRun } from '../types'
+import { MetricCard } from './MetricCard'
+import { TrendChart } from './TrendChart'
+import { TestSuiteCard } from './TestSuiteCard'
+
+export function OverviewTab({
+  goldenMetrics,
+  ragMetrics,
+  syntheticMetrics,
+  trendData,
+  testRuns,
+  isRunningGolden,
+  isRunningRag,
+  isRunningSynthetic,
+  runGoldenTests,
+  runRagTests,
+  runSyntheticTests,
+}: {
+  goldenMetrics: BQASMetrics | null
+  ragMetrics: BQASMetrics | null
+  syntheticMetrics: BQASMetrics | null
+  trendData: TrendData | null
+  testRuns: TestRun[]
+  isRunningGolden: boolean
+  isRunningRag: boolean
+  isRunningSynthetic: boolean
+  runGoldenTests: () => void
+  runRagTests: () => void
+  runSyntheticTests: () => void
+}) {
+  return (
+    <div className="space-y-6">
+      {/* Quick Stats */}
+      <div className="grid grid-cols-1 md:grid-cols-2 lg:grid-cols-4 gap-4">
+        <MetricCard
+          title="Golden Score"
+          value={goldenMetrics?.avg_composite_score.toFixed(2) || '-'}
+          subtitle="Durchschnitt aller Golden Tests"
+          trend={trendData?.trend === 'improving' ? 'up' : trendData?.trend === 'declining' ? 'down' : 'stable'}
+          color="blue"
+        />
+        <MetricCard
+          title="Pass Rate"
+          value={goldenMetrics ? `${((goldenMetrics.passed_tests / goldenMetrics.total_tests) * 100).toFixed(0)}%` : '-'}
+          subtitle={goldenMetrics ? `${goldenMetrics.passed_tests}/${goldenMetrics.total_tests} bestanden` : undefined}
+          color="green"
+        />
+        <MetricCard
+          title="RAG Qualitaet"
+          value={ragMetrics?.avg_composite_score.toFixed(2) || '-'}
+          subtitle="RAG Retrieval Score"
+          color="purple"
+        />
+        <MetricCard
+          title="Test Runs"
+          value={testRuns.length}
+          subtitle="Letzte 30 Tage"
+          color="yellow"
+        />
+      </div>
+
+      {/* Trend Chart */}
+      <div className="bg-white rounded-xl border border-slate-200 p-6">
+        <h3 className="text-lg font-semibold text-slate-900 mb-4">Score-Trend (30 Tage)</h3>
+        <TrendChart data={trendData || { dates: [], scores: [], trend: 'insufficient_data' }} />
+      </div>
+
+      {/* Test Suites Grid */}
+      <div className="grid grid-cols-1 lg:grid-cols-3 gap-6">
+        <TestSuiteCard
+          title="Golden Suite"
+          description="97 validierte Referenz-Tests fuer Intent-Erkennung"
+          metrics={goldenMetrics || undefined}
+          onRun={runGoldenTests}
+          isRunning={isRunningGolden}
+        />
+        <TestSuiteCard
+          title="RAG/Korrektur Tests"
+          description="EH-Retrieval, Operatoren-Alignment, Citation Tests"
+          metrics={ragMetrics || undefined}
+          onRun={runRagTests}
+          isRunning={isRunningRag}
+        />
+        <TestSuiteCard
+          title="Synthetic Tests"
+          description="LLM-generierte Variationen fuer Robustheit"
+          metrics={syntheticMetrics || undefined}
+          onRun={runSyntheticTests}
+          isRunning={isRunningSynthetic}
+        />
+      </div>
+    </div>
+  )
+}