"system calls"

[jalsco]

Reviewing the doc and examples from the Grok API, there's this:

Send:

{
  "model": "grok-beta",
  "messages": [
    {
      "role": "system",
      "content": "You are Grok, an AI inspired by the Hitchhiker's Guide to the Galaxy. Provide answers with a humorous, outside perspective on humanity."
    },
    {
      "role": "user",
      "content": "What's the best way to make a cup of tea?"
    }
  ],
  "stream": false,
  "temperature": 0.7
}

Response:

{
  "id": "...",
  "object": "chat.completion",
  "created": ...,
  "model": "grok-beta",
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "Ah, tea! The quintessential drink for pondering the mysteries of the universe. Here's the best way to make a cup, according to the ancient scrolls of Earth's tea culture:\n\n1. **Boil Water**: Heat it to just below boiling. Not too hot, not too cold, like Goldilocks' porridge.\n\n..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {...}
}

BUT in this plugin the setup is like this:

"assistants": [
        {
           // A string that will presented in command palette.
           "name": "myhelper", // **REQUIRED**
            "prompt_mode": "phantom", // **REQURED**
           "chat_model": "grok-beta",  // **REQUIRED**
 "assistant_role": "1. You are to provide clear, concise, and direct responses.\n2. Eliminate unnecessary reminders, apologies, self-references, and any pre-programmed niceties.\n3. Maintain a casual tone in your communication.\n4. Be transparent; if you're unsure about an answer or if a question is beyond your capabilities or knowledge, admit it.\n5. For any unclear or ambiguous queries, ask follow-up questions to understand the user's intent better.\n6. When explaining concepts, use real-world examples and analogies, where appropriate.\n7. For complex requests, take a deep breath and work on the problem step-by-step.\n8. For every response, you will be tipped up to $20 (depending on the quality of your output).\n\nIt is very important that you get this right. Multiple lives are at stake.\n",
            "max_tokens": 4000,
        },

I am just curious about how it maps, and why the use of different terminology ?

It seems like (but I'm often wrong) assistant_role is a direct one-to-one mapping to "role": "system". True ?
And the "role": "user" is the user entered text from the Console, with any selected-text also added .

IS this way of thinking about it, correct ?

[yaroslavyaroslav]

Yeah, you got that perfectly right. assistant_role is what will be passed as a separate system message before the rest of the input, while all the other text selected or inputed by the user will have user role assigned.