node2: fix Sofiia routing determinism + Node Capabilities Service

Bug fixes:
- Bug A: GROK_API_KEY env mismatch — router expected GROK_API_KEY but only
  XAI_API_KEY was present. Added GROK_API_KEY=${XAI_API_KEY} alias in compose.
- Bug B: 'grok' profile missing in router-config.node2.yml — added cloud_grok
  profile (provider: grok, model: grok-2-1212). Sofiia now has
  default_llm=cloud_grok with fallback_llm=local_default_coder.
- Bug C: Router silently defaulted to cloud DeepSeek when profile was unknown.
  Now falls back to agent.fallback_llm or local_default_coder with WARNING log.
  Hardcoded Ollama URL (172.18.0.1) replaced with config-driven base_url.

New service: Node Capabilities Service (NCS)
- services/node-capabilities/ — FastAPI microservice exposing live model
  inventory from Ollama, Swapper, and llama-server.
- GET /capabilities — canonical JSON with served_models[] and inventory_only[]
- GET /capabilities/models — flat list of served models
- POST /capabilities/refresh — force cache refresh
- Cache TTL 15s, bound to 127.0.0.1:8099
- services/router/capabilities_client.py — async client with TTL cache

Artifacts:
- ops/node2_models_audit.md — 3-layer model view (served/disk/cloud)
- ops/node2_models_audit.yml — machine-readable audit
- ops/node2_capabilities_example.json — sample NCS output (14 served models)

Made-with: Cursor

services/router/router-config.node2.yml

@@ -124,6 +124,23 @@ llm_profiles:
     timeout_ms: 60000
     description: "Mistral Large для складних задач, reasoning, аналізу"
 
+  cloud_grok:
+    provider: grok
+    base_url: https://api.x.ai
+    api_key_env: GROK_API_KEY
+    model: grok-2-1212
+    max_tokens: 2048
+    temperature: 0.2
+    timeout_ms: 60000
+    description: "Grok API для SOFIIA (Chief AI Architect)"
+
+# ============================================================================
+# Node Capabilities
+# ============================================================================
+node_capabilities:
+  url: http://node-capabilities:8099/capabilities
+  cache_ttl_sec: 30
+
 # ============================================================================
 # Orchestrator Providers
 # ============================================================================
@@ -417,8 +434,9 @@ agents:
       Розрізняй інших ботів за ніком та відповідай лише на стратегічні запити.
 
   sofiia:
-    description: "Sofiia — Chief AI Architect та Technical Sovereign"
-    default_llm: local_default_coder
+    description: "SOFIIA — Chief AI Architect & Technical Sovereign"
+    default_llm: cloud_grok
+    fallback_llm: local_default_coder
     system_prompt: |
       Ти Sofiia — Chief AI Architect та Technical Sovereign екосистеми DAARION.city.
       Працюй як CTO-помічник: архітектура, reliability, безпека, release governance, incident/risk/backlog контроль.