why is model required for chat completion?

[osseonews]

I don't understand why model is a required a param for the chat completions endpoint. The model is set in the Agent in the DO ocean dashboard when creating an Agent with Gradient AI, so why does this need to be sent? According to your docs: https://docs.digitalocean.com/products/gradient-ai-platform/how-to/use-agents/ you can just send the request as follows, no model is needed because it part of the settings of the agent. but on your Gradient.Chat.CompletionCreateParams a model is required?

curl -i \
  -X POST \
  $AGENT_ENDPOINT/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AGENT_ACCESS_KEY" \
  -d '{
    "messages": [
      {
        "role": "user",
        "content": "What is the capital of France?"
      }
    ],
    "stream": false,
    "include_functions_info": false,
    "include_retrieval_info": false,
    "include_guardrails_info": false
  }'