Switch ai-assistant to LiteLLM provider with task-specific models

Was defaulting to plain Ollama with gemma3:270m for every request -
no LLM_PROVIDER or LITELLM_* env vars were set. LiteLLM is already
deployed with purpose-built model aliases per task
(apps/litellm/base/configmap.yaml); this wires ai-assistant to use it.

apps/nxtgauge-ai-assistant/base/deployment.yaml

@@ -34,6 +34,17 @@ spec:
               value: "gemma3:270m"
             - name: OLLAMA_EMBED_MODEL
               value: "nomic-embed-text"
+            - name: LLM_PROVIDER
+              value: "litellm"
+            - name: LITELLM_BASE_URL
+              value: "http://litellm.nxtgauge-ai.svc.cluster.local:4000"
+            - name: LITELLM_MODEL
+              value: "askash-main"
+            - name: LITELLM_API_KEY
+              valueFrom:
+                secretKeyRef:
+                  name: litellm-secrets
+                  key: LITELLM_MASTER_KEY
             - name: NXTGAUGE_USERS_URL
               value: "http://nxtgauge-rust-users:9101"
             - name: AI_SERVICE_KEY