fix: add LLM_API_URL and LLM_MODEL to portfolio deployment

Missing env vars caused LLM calls to fail even with valid OAuth tokens.
Now pod has:
- Auth credentials (Authentik client_id/secret/token_url) ✅
- LLM endpoint (api.riotpiao.com/v1/chat/completions) ✅
- Model (qwen2.5:3b-instruct) ✅

Chat API will now successfully authenticate and call LLM gateway.

infra/portfolio/base/deployment.yaml

@@ -42,6 +42,11 @@ spec:
             secretKeyRef:
               name: portfolio-agent-oidc
               key: TOKEN_URL
+        # LLM API configuration
+        - name: LLM_API_URL
+          value: "https://api.riotpiao.com/v1/chat/completions"
+        - name: LLM_MODEL
+          value: "qwen2.5:3b-instruct"
         ports:
         - name: http
           containerPort: 3000