Macro Handler

Macro Handler

Android Automation Platform

Global ObjectNetwork and IntegrationSingleton Global

AI

Sends text or image prompts to the configured AI provider; the result is a table with ok, text and error.

Documented for app version 1.0.51Updated:

Detailed Explanation

This section explains when to use the API, how to call it, and which structures it works best with in production flow.

How To Call It

AI is a singleton global table: call its functions with a dot (AI.<method>(...)).

When To Use It

For network integration, use HTTPS only, keep the response size bounded, and validate the response code before moving into JSON or File steps.

Parameters and Return

AI offers 2 methods; each method page lists its parameters and return value.

Options and Limits

Rate limit: AI calls are limited to 20 per minute; past the limit the call raises an error that stops the macro unless it runs inside pcall.

Best Combined With

The most common pattern is to check a Request response with getResponseCode(), read its body with getData() and parse it with JSON.parse().

Example Usage

The snippet below is a starter pattern that can be applied directly in runtime flow.

lua
Try in Editor →
local answer = AI.ask("Summarise this log line in five words: level 3 cleared")
if answer.ok then print(answer.text) else print(answer.error) end

Copyable Progressive Examples

From foundation to combined usage, each level is provided as a separate code block so you can copy the level you need and adapt it directly.

Foundation

Shows the shortest direct way to call the API.

Foundation
lua
Try in Editor →
local answer = AI.ask("Summarise this log line in five words: level 3 cleared")
if answer.ok then print(answer.text) else print(answer.error) end

Simple

Wraps the base call with minimal flow control.

Simple
lua
Try in Editor →
local answer = AI.ask("Summarise this log line in five words: level 3 cleared")
if answer.ok then print(answer.text) else print(answer.error) end

-- Continue with one focused method on the object.

Practical Flow

A practical pattern for real macros with pcall, logging, and guards.

Practical Flow
lua
Try in Editor →
local answer = AI.ask("Summarise this log line in five words: level 3 cleared")
if answer.ok then print(answer.text) else print(answer.error) end
local note = "AI overview loaded"
print(note)

Detailed

This level packages the API into a reusable helper with error reporting.

Detailed
lua
Try in Editor →
-- For network integration, use HTTPS only, keep the response size bounded, and validate the response code before moving into JSON or File steps.
local function run_ai_step()
  local answer = AI.ask("Summarise this log line in five words: level 3 cleared")
  if answer.ok then print(answer.text) else print(answer.error) end
end

local ok, err = pcall(run_ai_step)
if not ok then
  toast("Step failed")
  print(err)
end

Combined

Combines the API with related structures to form a more realistic workflow.

Combined
lua
Try in Editor →
local answer = AI.ask("Summarise this log line in five words: level 3 cleared")
if answer.ok then print(answer.text) else print(answer.error) end
KV.set("last_network_step", DateTime.now():format("yyyy-MM-dd HH:mm:ss"))
print("Network step finished")