feat: v0.0.1 - Groq provider, timezone, journal context, test connection, task logging

Added:
- Groq AI provider (free, fast with llama-3.3-70b-versatile)
- Timezone setting (22 timezones)
- Journal context: include previous journals (3/7/14/30 days)
- Test connection button for AI providers
- Per-provider settings (API key, model, base URL remembered)
- Detailed task logging (full prompts and responses)
- Tasks page with expandable details
- Progress modal with steps and AI output details

Fixed:
- Groq API endpoint (https://api.groq.com/openai/v1/chat/completions)
- Ollama baseUrl leaking to other providers
- Database schema references
- Proper Prisma migrations (data-safe)

Changed:
- Default AI: OpenAI → Groq
- Project renamed: TotalRecall → DearDiary
- Strict anti-hallucination prompt
- Docker uses prisma migrate deploy (non-destructive)

backend/src/routes/settings.ts

@@ -31,7 +31,7 @@ settingsRoutes.put('/', async (c) => {
   const data: Record<string, unknown> = {};
   if (aiProvider !== undefined) data.aiProvider = aiProvider;
   if (aiApiKey !== undefined) data.aiApiKey = aiApiKey;
-  if (aiModel !== undefined) data.aiModel = aiModel || 'gpt-4';
+  if (aiModel !== undefined) data.aiModel = aiModel;
   if (aiBaseUrl !== undefined) data.aiBaseUrl = aiBaseUrl;
   if (journalPrompt !== undefined) data.journalPrompt = journalPrompt;
   if (language !== undefined) data.language = language;
@@ -67,3 +67,34 @@ settingsRoutes.post('/validate-key', async (c) => {
     return c.json({ data: { valid: false }, error: null });
   }
 });
+
+settingsRoutes.post('/test', async (c) => {
+  const body = await c.req.json();
+  const { provider, apiKey, model, baseUrl } = body;
+
+  if (!provider) {
+    return c.json({ data: null, error: { code: 'VALIDATION_ERROR', message: 'provider is required' } }, 400);
+  }
+
+  const { createAIProvider } = await import('../services/ai/provider');
+  
+  try {
+    const aiProvider = createAIProvider({
+      provider,
+      apiKey: apiKey || '',
+      model: model || undefined,
+      baseUrl: baseUrl || undefined,
+    });
+    
+    const result = await aiProvider.generate('Say "OK" if you can read this.', 'You are a test assistant. Respond with just "OK".');
+    
+    if (result.toLowerCase().includes('ok')) {
+      return c.json({ data: { valid: true, message: 'Connection successful!' }, error: null });
+    } else {
+      return c.json({ data: { valid: false }, error: { code: 'TEST_FAILED', message: 'Model responded but with unexpected output' } });
+    }
+  } catch (err) {
+    const message = err instanceof Error ? err.message : 'Connection failed';
+    return c.json({ data: { valid: false }, error: { code: 'TEST_FAILED', message } });
+  }
+});