Switch AI model from kimi-k2.5 to qwen/qwen3.5-397b-a17b

kimi-k2.5 is a thinking model that times out on complex prompts (>3min).
qwen3.5-397b-a17b responds in ~2s with clean JSON output.

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

.env.example

@@ -8,5 +8,5 @@ NODE_ENV=development
 
 # AI Investment Advisor (OpenAI-compatible API)
 AI_API_URL=https://integrate.api.nvidia.com/v1
-AI_API_KEY=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
-AI_MODEL=moonshotai/kimi-k2.5
+AI_API_KEY=your_nvidia_api_key_here
+AI_MODEL=qwen/qwen3.5-397b-a17b

backend/src/modules/investment-planning/investment-planning.service.ts

@@ -402,7 +402,7 @@ Based on this complete financial picture, provide your investment recommendation
   private async callAI(messages: Array<{ role: string; content: string }>): Promise<AIResponse> {
     const apiUrl = this.configService.get<string>('AI_API_URL') || 'https://integrate.api.nvidia.com/v1';
     const apiKey = this.configService.get<string>('AI_API_KEY');
-    const model = this.configService.get<string>('AI_MODEL') || 'moonshotai/kimi-k2.5';
+    const model = this.configService.get<string>('AI_MODEL') || 'qwen/qwen3.5-397b-a17b';
 
     if (!apiKey) {
       this.logger.error('AI_API_KEY not configured');