P1: NCS-first model selection + NATS capabilities + Grok 4.1

Router model selection:
- New model_select.py: resolve_effective_profile → profile_requirements →
  select_best_model pipeline. NCS-first with graceful static fallback.
- selection_policies in router-config.node2.yml define prefer order per
  profile without hardcoding models (e.g. local_default_coder prefers
  qwen3:14b then qwen3.5:35b-a3b).
- Cloud profiles (cloud_grok, cloud_deepseek) skip NCS; on cloud failure
  use fallback_profile via NCS for local selection.
- Structured logs: selected_profile, required_type, runtime, model,
  caps_age_s, fallback_reason on every infer request.

Grok model fix:
- grok-2-1212 no longer exists on xAI API → updated to
  grok-4-1-fast-reasoning across all 3 hardcoded locations in main.py
  and router-config.node2.yml.

NCS NATS request/reply:
- node-capabilities subscribes to node.noda2.capabilities.get (NATS
  request/reply). Enabled via ENABLE_NATS_CAPS=true in compose.
- NODA1 router can query NODA2 capabilities over NATS leafnode without
  HTTP connectivity.

Verified:
- NCS: 14 served models from Ollama+Swapper+llama-server
- NATS: request/reply returns full capabilities JSON
- Sofiia: cloud_grok → grok-4-1-fast-reasoning (tested, 200 OK)
- Helion: NCS → qwen3:14b via Ollama (caps_age=23.7s cache hit)
- Router health: ok

Made-with: Cursor

services/node-capabilities/main.py

@@ -240,6 +240,55 @@ async def capabilities_refresh():
     return JSONResponse(content={"refreshed": True, "served_count": data["served_count"]})
 
 
+# ── NATS request/reply (optional) ─────────────────────────────────────────────
+
+ENABLE_NATS = os.getenv("ENABLE_NATS_CAPS", "false").lower() in ("true", "1", "yes")
+NATS_URL = os.getenv("NATS_URL", "nats://dagi-nats:4222")
+NATS_SUBJECT = f"node.{NODE_ID.lower()}.capabilities.get"
+
+_nats_client = None
+
+
+async def _nats_capabilities_handler(msg):
+    """Handle NATS request/reply for capabilities."""
+    import json as _json
+    try:
+        data = await _build_capabilities()
+        payload = _json.dumps(data).encode()
+        if msg.reply:
+            await _nats_client.publish(msg.reply, payload)
+            logger.debug(f"NATS reply sent to {msg.reply} ({len(payload)} bytes)")
+    except Exception as e:
+        logger.warning(f"NATS handler error: {e}")
+        if msg.reply and _nats_client:
+            await _nats_client.publish(msg.reply, b'{"error":"internal"}')
+
+
+@app.on_event("startup")
+async def startup_nats():
+    global _nats_client
+    if not ENABLE_NATS:
+        logger.info(f"NATS capabilities disabled (ENABLE_NATS_CAPS={ENABLE_NATS})")
+        return
+    try:
+        import nats as nats_lib
+        _nats_client = await nats_lib.connect(NATS_URL)
+        await _nats_client.subscribe(NATS_SUBJECT, cb=_nats_capabilities_handler)
+        logger.info(f"✅ NATS subscribed: {NATS_SUBJECT} on {NATS_URL}")
+    except Exception as e:
+        logger.warning(f"⚠️ NATS init failed (non-fatal): {e}")
+        _nats_client = None
+
+
+@app.on_event("shutdown")
+async def shutdown_nats():
+    if _nats_client:
+        try:
+            await _nats_client.close()
+        except Exception:
+            pass
+
+
 if __name__ == "__main__":
     import uvicorn
     uvicorn.run(app, host="0.0.0.0", port=int(os.getenv("PORT", "8099")))

services/node-capabilities/requirements.txt

@@ -1,3 +1,4 @@
 fastapi>=0.110.0
 uvicorn>=0.29.0
 httpx>=0.27.0
+nats-py>=2.7.0