using EditAction API to build an "inline prompt" feature

[bcp-dev-ops]

Looking for some help building out a feature. Basically looking for a way to be able to write prompts "inline" and then iteratively execute the whole file, using the current line as a prompt. (I think this could be a workflow gamechanger.)

For example, if I wanted to write a prompt on line 6 (to insert the result after line 6), I could write a comment like: "// Write a function that prints "Hello, World!" to the console"

example.js

let foo = 'bar';

const HelloWorldMainComponent = (props) => {
  return <h1>Hello</h1>;
};
// Write a function that prints "Hello, World!" to the console
// (And then ChatGPT response would be injected here)
export default HelloWorldMainComponent;

Here is my lua function, but getting stuck trying to figure out how to use the EditAction

local function run_with_context()
    local current_line = vim.api.nvim_get_current_line()
    local current_line_number = vim.api.nvim_win_get_cursor(0)[1]
    local extended_prompt = current_line
        .. ". Insert at line "
        .. current_line_number
        .. "."
    local EditAction = require("chatgpt.flows.actions.edits")
    local opts = {
        params = {
            model = "gpt-3.5-turbo",
            stop = {
                "```",
            },
        },
        template = extended_prompt,
        variables = {},
        strategy = "edit",
    }
    local action = EditAction.new(opts)
    action:run()
end

Spinning my wheels a bit here-- getting an API error on the result: // API ERROR: 'instruction' is a required property

Been playing around for an hour but have run out of time, will continue to experiment over the upcoming days. Any ideas on how to help?

[jackMort]

I'm not sure if I understood it correctly, but there is a CodeCompletion feature showcased here: https://youtu.be/7k0KZsheLP4?si=-htsXx8ErRjG62ER&t=387. Is this what you are looking for?

[bcp-dev-ops]

Ah not quite-- unless the CodeCompletion feature also works with prompts?

I'm looking to write a prompt inline and get the result inline (not necessarily write partial code inline and get the result inline)

[ben-wall]

Could this be related to https://github.com/jackMort/ChatGPT.nvim/issues/285 ?