integrate arch with model_server

arch/envoy.template.yaml

@@ -211,8 +211,7 @@ static_resources:
                       domains:
                         - "*"
                       routes:
-
-                        {% for internal_clustrer in ["embeddings", "zeroshot", "guard", "arch_fc", "hallucination"] %}
+                        {% for internal_clustrer in ["embeddings", "zeroshot", "guard", "arch_fc", "hallucination", "model_server"] %}
                         - match:
                             prefix: "/"
                             headers:
@@ -449,7 +448,7 @@ static_resources:
         typed_config:
           "@type": type.googleapis.com/envoy.extensions.transport_sockets.tls.v3.UpstreamTlsContext
           sni: api.mistral.ai
-    {% for internal_clustrer in ["embeddings", "zeroshot", "guard", "arch_fc", "hallucination"] %}
+    {% for internal_clustrer in ["embeddings", "zeroshot", "guard", "arch_fc", "hallucination", "model_server"] %}
     - name: {{ internal_clustrer }}
       connect_timeout: 5s
       type: STRICT_DNS

arch/tools/cli/config_generator.py

@@ -90,6 +90,7 @@ def validate_and_render_schema():
 
     rendered = template.render(data)
     print(ENVOY_CONFIG_FILE_RENDERED)
+    print(rendered)
     with open(ENVOY_CONFIG_FILE_RENDERED, "w") as file:
         file.write(rendered)