Sign in

v1

latestOpenAPI 3.0.32026-07-26131237.0 KB
Commands

Execute simple action 4

Issues ACTION 4 to the specified game session.
This is a single-parameter command (no X/Y coordinates): the exact in-game effect depends on the title—for example, it might represent “move right" or “select option D”.

The request must include: • game_id — which game to act on
• guid — the active session identifier returned from RESET

An optional reasoning JSON blob (≤ 16 KB) can be attached for audit or research purposes.

A successful call returns the next visual frame(s) and updated score/state.

post/api/cmd/ACTION4

Request body

game_idstring required

Game identifier this action targets.

guidstring required

Server-generated session ID obtained from a RESET response.

reasoningobject

Optional, caller-defined JSON blob (≤ 16 KB) capturing the agent's internal reasoning, model parameters, or any other metadata you'd like to store alongside the action.

Response

Frame returned after executing the action.

game_idstring required

Game identifier for the running session.

guidstring required

Server-generated session ID; use this for all subsequent commands.

state'NOT_FINISHED' | 'NOT_STARTED' | 'WIN' | 'GAME_OVER' required

Current state of the session:

• NOT_FINISHED - game in progress, not yet WIN or GAME_OVER.
• NOT_STARTED - session has ended (WIN or GAME_OVER) and requires RESET.
• WIN - session ended in victory.
• GAME_OVER - session ended in defeat.

levels_completedinteger required

Current cumulative number of levels completed for this run.

win_levelsinteger required

Level threshold required to reach the WIN state. Mirrors the game's configured win condition so agents can adapt dynamically without hard-coding values.

available_actionsinteger[] required

List of available actions for the current game.