better model names (#517)

demos/samples_python/currency_exchange/arch_config.yaml

@@ -8,10 +8,8 @@ listeners:
     timeout: 30s
 
 llm_providers:
-  - name: gpt-4o
-    access_key: $OPENAI_API_KEY
-    provider_interface: openai
-    model: gpt-4o
+  - access_key: $OPENAI_API_KEY
+    model: openai/gpt-4o
 
 endpoints:
   frankfurther_api:

demos/samples_python/human_resources_agent/arch_config.yaml

@@ -9,10 +9,8 @@ listeners:
 
 # Centralized way to manage LLMs, manage keys, retry logic, failover and limits in a central way
 llm_providers:
-  - name: OpenAI
-    provider_interface: openai
-    access_key: $OPENAI_API_KEY
-    model: gpt-4o-mini
+  - access_key: $OPENAI_API_KEY
+    model: openai/gpt-4o-mini
     default: true
 
 # Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.

demos/samples_python/multi_turn_rag_agent/arch_config.yaml

@@ -13,10 +13,8 @@ endpoints:
     connect_timeout: 0.005s
 
 llm_providers:
-  - name: gpt-4o-mini
-    access_key: $OPENAI_API_KEY
-    provider_interface: openai
-    model: gpt-4o-mini
+  - access_key: $OPENAI_API_KEY
+    model: openai/gpt-4o-mini
     default: true
 
 system_prompt: |

demos/samples_python/network_switch_operator_agent/arch_config.yaml

@@ -8,10 +8,8 @@ listeners:
 
 # Centralized way to manage LLMs, manage keys, retry logic, failover and limits in a central way
 llm_providers:
-  - name: OpenAI
-    provider_interface: openai
-    access_key: $OPENAI_API_KEY
-    model: gpt-4o
+  - access_key: $OPENAI_API_KEY
+    model: openai/gpt-4o
     default: true
 
 # default system prompt used by all prompt targets

demos/samples_python/stock_quote/arch_config.yaml

@@ -8,10 +8,8 @@ listeners:
     timeout: 30s
 
 llm_providers:
-  - name: gpt-4o
-    access_key: $OPENAI_API_KEY
-    provider_interface: openai
-    model: gpt-4o
+  - access_key: $OPENAI_API_KEY
+    model: openai/gpt-4o
 
 endpoints:
   twelvedata_api:

demos/samples_python/weather_forecast/arch_config.yaml

@@ -17,15 +17,11 @@ overrides:
   prompt_target_intent_matching_threshold: 0.6
 
 llm_providers:
-  - name: groq
-    access_key: $GROQ_API_KEY
-    provider_interface: groq
-    model: llama-3.2-3b-preview
+  - access_key: $GROQ_API_KEY
+    model: groq/llama-3.2-3b-preview
 
-  - name: gpt-4o
-    access_key: $OPENAI_API_KEY
-    provider_interface: openai
-    model: gpt-4o
+  - access_key: $OPENAI_API_KEY
+    model: openai/gpt-4o
     default: true
 
 system_prompt: |