env/task_graders.py

"""
Registered agent graders — one enabled grader per task (easy / medium / hard).

Automated checks count tasks that declare a grader and can run episode scoring.
All three share the same history-based rubric; difficulty is enforced by the
environment dynamics (items + volatility), not by different formulas.
"""

from __future__ import annotations

from typing import Any, Callable, Dict, List

from env.grader import evaluate_episode

History = List[Dict[str, Any]]


def easy_agent_grader(history: History) -> float:
    return evaluate_episode(history)


def medium_agent_grader(history: History) -> float:
    return evaluate_episode(history)


def hard_agent_grader(history: History) -> float:
    return evaluate_episode(history)


# Explicit registry (imported by server /tasks and static analysis)
TASK_AGENT_GRADERS: Dict[str, Callable[[History], float]] = {
    "easy": easy_agent_grader,
    "medium": medium_agent_grader,
    "hard": hard_agent_grader,
}