Add support for multiple GenAI Providers (#22144)

* GenAI client manager

* Add config migration

* Convert to roles list

* Support getting client via manager

* Cleanup

* Fix import issues

* Set model in llama.cpp config

* Clenaup

* Use config update

* Clenaup

* Add new title and desc

frigate/genai/llama_cpp.py

@@ -67,6 +67,7 @@ class LlamaCppClient(GenAIClient):
 
             # Build request payload with llama.cpp native options
             payload = {
+                "model": self.genai_config.model,
                 "messages": [
                     {
                         "role": "user",
@@ -134,6 +135,7 @@ class LlamaCppClient(GenAIClient):
                     openai_tool_choice = "required"
 
             payload = {
+                "model": self.genai_config.model,
                 "messages": messages,
             }