scenarios/delayed_recall_keys_8x8.json

{
    "scenario_id": "delayed_recall_keys_8x8",
    "type": "pattern_memory",
    "seed": 2289,
    "board_width": 8,
    "board_height": 8,
    "hazard_count": 12,
    "key_count": 5,
    "max_steps": 30,
    "max_hazard_reveals": 2,
    "signal_mode": "count",
    "flags_count": 15,
    "difficulty": "hard",
    "description": "8x8 grid, 12 hazards, 5 keys. 10 cells flash for 4 steps showing a mix of keys, hazards, and signals — then disappear. The agent must collect all 5 keys to win. After the flash fades, the agent must recall which flashed cells contained keys (safe to reveal) vs hazards (fatal to reveal). Revealing a remembered-hazard cell costs a life. This tests long-horizon memory: the recall happens 10-20 steps after the flash.",
    "how_to_play": "10 cells flash for 4 steps showing keys, hazards, and signals — memorize them! After they fade, you must find and reveal all 5 keys (gold cells) to win. Avoid revealing cells you remember as hazards. Use signal numbers to navigate safely to key locations.",
    "tags": ["delayed_recall", "partial_observability", "multi_stage_solution"],
    "flash_cells": [[0,0],[0,7],[1,3],[2,5],[3,1],[3,6],[5,2],[5,5],[7,0],[7,7]],
    "flash_until_step": 4,
    "win_condition": {
        "type": "collect_keys"
    }
}