test: add Playwright tests and debug endpoint for AI provider validation

Add comprehensive tests to verify AI provider configuration and ensure
OpenAI is being used correctly instead of hardcoded Ollama.

Changes:
- Add ai-provider.spec.ts: Playwright tests for AI provider validation
- Add /api/debug/config endpoint: Exposes AI configuration for testing
- Tests verify: OpenAI config, connectivity, no OLLAMA errors

All 4 tests pass locally:
✓ AI provider configuration check
✓ OpenAI connectivity test
✓ Embeddings provider verification
✓ No OLLAMA errors validation

Usage on Docker:
TEST_URL=http://192.168.1.190:3000 npx playwright test ai-provider.spec.ts

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

keep-notes/app/api/debug/config/route.ts

@@ -0,0 +1,32 @@
+import { NextResponse } from 'next/server';
+import { getSystemConfig } from '@/lib/config';
+
+/**
+ * Debug endpoint to check AI configuration
+ * This helps verify that OpenAI is properly configured
+ */
+export async function GET() {
+  try {
+    const config = await getSystemConfig();
+
+    // Return only AI-related config for debugging
+    const aiConfig = {
+      AI_PROVIDER_TAGS: config.AI_PROVIDER_TAGS || 'not set',
+      AI_PROVIDER_EMBEDDING: config.AI_PROVIDER_EMBEDDING || 'not set',
+      AI_MODEL_TAGS: config.AI_MODEL_TAGS || 'not set',
+      AI_MODEL_EMBEDDING: config.AI_MODEL_EMBEDDING || 'not set',
+      OPENAI_API_KEY: config.OPENAI_API_KEY ? 'set (hidden)' : 'not set',
+      OLLAMA_BASE_URL: config.OLLAMA_BASE_URL || 'not set',
+      OLLAMA_MODEL: config.OLLAMA_MODEL || 'not set',
+      CUSTOM_OPENAI_BASE_URL: config.CUSTOM_OPENAI_BASE_URL || 'not set',
+      CUSTOM_OPENAI_API_KEY: config.CUSTOM_OPENAI_API_KEY ? 'set (hidden)' : 'not set',
+    };
+
+    return NextResponse.json(aiConfig);
+  } catch (error) {
+    return NextResponse.json(
+      { error: 'Failed to get config', details: error },
+      { status: 500 }
+    );
+  }
+}