feat(models): add x-ai/grok-4.3 to OpenRouter + Nous Portal curated lists (#20497)

Endpoint validated over 6 conversational turns with tool calls (9 API
calls, 3 tool calls, 0 failures) and an 8-request burst (8/8 ok,
0 rate limits). Latency ~5-10s/call — slower than grok-4.20 but
expected for a reasoning model.

- hermes_cli/models.py: add to OPENROUTER_MODELS and _PROVIDER_MODELS['nous']
- website/static/api/model-catalog.json: regenerated

website/static/api/model-catalog.json

@@ -1,6 +1,6 @@
 {
   "version": 1,
-  "updated_at": "2026-05-06T00:37:26Z",
+  "updated_at": "2026-05-06T02:14:51Z",
   "metadata": {
     "source": "hermes-agent repo",
     "docs": "https://hermes-agent.nousresearch.com/docs/reference/model-catalog"
@@ -128,6 +128,10 @@
           "id": "x-ai/grok-4.20",
           "description": ""
         },
+        {
+          "id": "x-ai/grok-4.3",
+          "description": ""
+        },
         {
           "id": "nvidia/nemotron-3-super-120b-a12b",
           "description": ""
@@ -242,6 +246,9 @@
         {
           "id": "x-ai/grok-4.20-beta"
         },
+        {
+          "id": "x-ai/grok-4.3"
+        },
         {
           "id": "nvidia/nemotron-3-super-120b-a12b"
         },