File size: 5,110 Bytes
2ce1061
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
# server/environment.py
# Core environment: manages episode state, dispatches to task banks and graders.

import random
from uuid import uuid4
from typing import Optional

from openenv.core.env_server.interfaces import Environment
from openenv.core.env_server.types import State

from models import DebugAction, DebugObservation, DebugState
from server.tasks.task_easy import get_random_easy_task
from server.tasks.task_medium import get_random_medium_task
from server.tasks.task_hard import get_random_hard_task
from server.graders.grader_easy import grade_easy
from server.graders.grader_medium import grade_medium
from server.graders.grader_hard import grade_hard


TASK_GETTERS = {
    "easy": get_random_easy_task,
    "medium": get_random_medium_task,
    "hard": get_random_hard_task,
}

GRADERS = {
    "easy": grade_easy,
    "medium": grade_medium,
    "hard": grade_hard,
}

MAX_STEPS = 3


class CodeDebugEnvironment(Environment):
    """
    OpenEnv environment for LLM-based code debugging.
    Supports 3 difficulty levels with partial rewards.
    """

    def __init__(self):
        self._episode_id: str = str(uuid4())
        self._difficulty: str = "easy"
        self._current_task: Optional[dict] = None
        self._step_count: int = 0
        self._best_reward: float = 0.0
        self._current_reward: float = 0.0
        self._done: bool = False

    def reset(self, difficulty: Optional[str] = None) -> DebugObservation:
        """
        Start a new episode. Optionally specify difficulty: easy | medium | hard.
        If not specified, cycles randomly.
        """
        self._episode_id = str(uuid4())
        self._step_count = 0
        self._best_reward = 0.0
        self._current_reward = 0.0
        self._done = False

        # Validate difficulty
        if difficulty and difficulty in TASK_GETTERS:
            self._difficulty = difficulty
        else:
            self._difficulty = random.choice(["easy", "medium", "hard"])

        # Load a task
        self._current_task = TASK_GETTERS[self._difficulty]()

        return DebugObservation(
            task_id=self._current_task["task_id"],
            difficulty=self._difficulty,
            buggy_code=self._current_task["buggy_code"],
            instructions=self._current_task["instructions"],
            test_cases_description=self._current_task["test_cases_description"],
            reward=None,
            passed_tests=None,
            total_tests=len(self._current_task["test_cases"]),
            feedback=None,
            done=False,
        )

    def step(self, action: DebugAction) -> DebugObservation:
        """
        Agent submits fixed_code (and optionally explanation for hard tasks).
        Returns observation with reward, feedback, and done flag.
        """
        if self._done:
            return DebugObservation(
                task_id=self._current_task["task_id"] if self._current_task else "none",
                difficulty=self._difficulty,
                buggy_code=self._current_task["buggy_code"] if self._current_task else "",
                instructions="Episode is already done. Call reset() to start a new episode.",
                test_cases_description="",
                reward=self._best_reward,
                passed_tests=None,
                total_tests=0,
                feedback="Episode ended. Please call reset() to start a new task.",
                done=True,
            )

        self._step_count += 1

        # Grade the submission
        grader = GRADERS[self._difficulty]
        if self._difficulty == "hard":
            reward, passed, total, feedback, _ = grader(
                action.fixed_code, self._current_task, action.explanation
            )
        else:
            reward, passed, total, feedback, _ = grader(
                action.fixed_code, self._current_task
            )

        self._current_reward = reward
        self._best_reward = max(self._best_reward, reward)

        # Episode ends if: perfect score OR max steps reached
        done = (reward == 1.0) or (self._step_count >= MAX_STEPS)
        self._done = done

        return DebugObservation(
            task_id=self._current_task["task_id"],
            difficulty=self._difficulty,
            buggy_code=self._current_task["buggy_code"],
            instructions=self._current_task["instructions"],
            test_cases_description=self._current_task["test_cases_description"],
            reward=reward,
            passed_tests=passed,
            total_tests=total,
            feedback=feedback,
            done=done,
        )

    @property
    def state(self) -> DebugState:
        """Return current episode metadata."""
        return DebugState(
            episode_id=self._episode_id,
            step_count=self._step_count,
            task_id=self._current_task["task_id"] if self._current_task else "none",
            difficulty=self._difficulty,
            max_steps=MAX_STEPS,
            current_reward=self._current_reward,
            best_reward=self._best_reward,
            done=self._done,
        )