File size: 10,796 Bytes
27cdb3e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
"""
Tests for the Reward Engine — 100% coverage of all reward signals.
"""

import pytest
from rewards.engine import RewardEngine
from executor.docker_executor import ExecutionResult
from scenarios.registry import Scenario


def _make_scenario(**kwargs):
    """Create a test scenario with sensible defaults."""
    defaults = dict(
        id="test_scenario",
        level=1,
        description="Test scenario",
        initial_state={},
        success_condition=lambda output: "success" in output.lower(),
        hint_commands=["pip install flask"],
        error_fingerprint=r"ModuleNotFoundError",
    )
    defaults.update(kwargs)
    return Scenario(**defaults)


def _make_result(**kwargs):
    """Create a test ExecutionResult with sensible defaults."""
    defaults = dict(stdout="", stderr="", exit_code=0, timed_out=False, blocked=False, block_reason="")
    defaults.update(kwargs)
    return ExecutionResult(**defaults)


class TestRewardSuccess:
    """Test the success reward signal."""

    def test_success_gives_positive_reward(self):
        engine = RewardEngine()
        scenario = _make_scenario()
        result = _make_result(stdout="Successfully installed flask\nSuccess")
        total, breakdown = engine.compute_reward(
            action="pip install flask",
            result=result,
            scenario=scenario,
            step_count=1,
            command_history=["pip install flask"],
            prev_error_log="ModuleNotFoundError",
            curr_error_log="Successfully installed flask",
        )
        assert breakdown.get("success", 0) == 10.0
        assert total > 0

    def test_no_success_gives_no_success_reward(self):
        engine = RewardEngine()
        scenario = _make_scenario()
        result = _make_result(stdout="some output", stderr="still broken")
        total, breakdown = engine.compute_reward(
            action="ls",
            result=result,
            scenario=scenario,
            step_count=1,
            command_history=["ls"],
            prev_error_log="error",
            curr_error_log="still broken",
        )
        assert "success" not in breakdown


class TestRewardCorrectCommand:
    """Test the correct_command reward signal."""

    def test_hint_command_gets_bonus(self):
        engine = RewardEngine()
        scenario = _make_scenario(hint_commands=["pip install flask"])
        result = _make_result(stdout="installed")
        total, breakdown = engine.compute_reward(
            action="pip install flask",
            result=result,
            scenario=scenario,
            step_count=1,
            command_history=["pip install flask"],
            prev_error_log="error",
            curr_error_log="installed",
        )
        assert breakdown.get("correct_command", 0) == 1.5

    def test_wrong_command_no_bonus(self):
        engine = RewardEngine()
        scenario = _make_scenario(hint_commands=["pip install flask"])
        result = _make_result(stdout="output")
        total, breakdown = engine.compute_reward(
            action="apt-get install python",
            result=result,
            scenario=scenario,
            step_count=1,
            command_history=["apt-get install python"],
            prev_error_log="error",
            curr_error_log="output",
        )
        assert "correct_command" not in breakdown


class TestRewardProgress:
    """Test the progress and no_progress signals."""

    def test_progress_when_error_changes(self):
        engine = RewardEngine()
        scenario = _make_scenario()
        result = _make_result(stdout="new output")
        total, breakdown = engine.compute_reward(
            action="pip install flask",
            result=result,
            scenario=scenario,
            step_count=1,
            command_history=["pip install flask"],
            prev_error_log="ModuleNotFoundError: No module named 'flask'",
            curr_error_log="installed successfully",
        )
        assert breakdown.get("progress", 0) == 1.0

    def test_no_progress_when_identical_logs(self):
        engine = RewardEngine()
        scenario = _make_scenario()
        result = _make_result(stdout="same error")
        same_log = "ModuleNotFoundError: No module named 'flask'"
        total, breakdown = engine.compute_reward(
            action="echo hello",
            result=result,
            scenario=scenario,
            step_count=2,
            command_history=["echo hello"],
            prev_error_log=same_log,
            curr_error_log=same_log,
        )
        assert breakdown.get("no_progress", 0) == -1.0


class TestRewardEfficiency:
    """Test the efficiency_bonus signal."""

    def test_efficiency_bonus_when_solved_fast(self):
        engine = RewardEngine()
        scenario = _make_scenario(hint_commands=["pip install flask"])
        result = _make_result(stdout="Success")
        total, breakdown = engine.compute_reward(
            action="pip install flask",
            result=result,
            scenario=scenario,
            step_count=1,
            command_history=["pip install flask"],
            prev_error_log="error",
            curr_error_log="Success",
        )
        assert breakdown.get("efficiency_bonus", 0) == 2.0

    def test_no_efficiency_bonus_when_too_many_steps(self):
        engine = RewardEngine()
        scenario = _make_scenario(hint_commands=["pip install flask"])
        result = _make_result(stdout="Success")
        total, breakdown = engine.compute_reward(
            action="pip install flask",
            result=result,
            scenario=scenario,
            step_count=5,
            command_history=["a", "b", "c", "d", "pip install flask"],
            prev_error_log="error",
            curr_error_log="Success",
        )
        assert "efficiency_bonus" not in breakdown


class TestRewardPenalties:
    """Test penalty signals."""

    def test_blocked_command_penalty(self):
        engine = RewardEngine()
        scenario = _make_scenario()
        result = _make_result(blocked=True, block_reason="Command 'foo' is not in the whitelist")
        total, breakdown = engine.compute_reward(
            action="foo",
            result=result,
            scenario=scenario,
            step_count=1,
            command_history=["foo"],
            prev_error_log="error",
            curr_error_log="blocked",
        )
        assert breakdown.get("invalid_command", 0) == -2.0

    def test_dangerous_command_penalty(self):
        engine = RewardEngine()
        scenario = _make_scenario()
        result = _make_result(blocked=True, block_reason="Dangerous blocklist pattern matched")
        total, breakdown = engine.compute_reward(
            action="rm -rf /",
            result=result,
            scenario=scenario,
            step_count=1,
            command_history=["rm -rf /"],
            prev_error_log="error",
            curr_error_log="blocked",
        )
        assert breakdown.get("dangerous_command", 0) == -10.0

    def test_timeout_penalty(self):
        engine = RewardEngine()
        scenario = _make_scenario()
        result = _make_result(timed_out=True)
        total, breakdown = engine.compute_reward(
            action="sleep 100",
            result=result,
            scenario=scenario,
            step_count=1,
            command_history=["sleep 100"],
            prev_error_log="error",
            curr_error_log="timeout",
        )
        assert breakdown.get("timeout", 0) == -5.0

    def test_repeated_command_penalty(self):
        engine = RewardEngine()
        scenario = _make_scenario()
        result = _make_result(stdout="output")
        total, breakdown = engine.compute_reward(
            action="pip install flask",
            result=result,
            scenario=scenario,
            step_count=2,
            command_history=["pip install flask", "pip install flask"],
            prev_error_log="error",
            curr_error_log="output",
        )
        assert breakdown.get("repeated_command", 0) == -1.5

    def test_step_cost_always_applied(self):
        engine = RewardEngine()
        scenario = _make_scenario()
        result = _make_result(stdout="output")
        total, breakdown = engine.compute_reward(
            action="ls",
            result=result,
            scenario=scenario,
            step_count=1,
            command_history=["ls"],
            prev_error_log="error",
            curr_error_log="output",
        )
        assert breakdown.get("step_cost", 0) == -0.2


class TestRewardCombinations:
    """Test reward signal combinations."""

    def test_perfect_solve_gives_max_reward(self):
        engine = RewardEngine()
        scenario = _make_scenario(hint_commands=["pip install flask"])
        result = _make_result(stdout="Successfully installed flask. Success")
        total, breakdown = engine.compute_reward(
            action="pip install flask",
            result=result,
            scenario=scenario,
            step_count=1,
            command_history=["pip install flask"],
            prev_error_log="ModuleNotFoundError",
            curr_error_log="installed",
        )
        # Should get: success(10) + correct_command(1.5) + progress(1) + efficiency(2) + step_cost(-0.2) = 14.3
        assert total > 14.0
        assert "success" in breakdown
        assert "correct_command" in breakdown
        assert "efficiency_bonus" in breakdown

    def test_blocked_command_short_circuits(self):
        """Blocked commands should only get step_cost + the block penalty."""
        engine = RewardEngine()
        scenario = _make_scenario()
        result = _make_result(blocked=True, block_reason="not in whitelist")
        total, breakdown = engine.compute_reward(
            action="foo",
            result=result,
            scenario=scenario,
            step_count=1,
            command_history=["foo"],
            prev_error_log="error",
            curr_error_log="blocked",
        )
        assert len(breakdown) == 2  # step_cost + invalid_command
        assert "success" not in breakdown
        assert "progress" not in breakdown

    def test_timed_out_short_circuits(self):
        """Timed out commands should only get step_cost + timeout penalty."""
        engine = RewardEngine()
        scenario = _make_scenario()
        result = _make_result(timed_out=True)
        total, breakdown = engine.compute_reward(
            action="sleep 999",
            result=result,
            scenario=scenario,
            step_count=1,
            command_history=["sleep 999"],
            prev_error_log="error",
            curr_error_log="timeout",
        )
        assert len(breakdown) == 2  # step_cost + timeout
        assert total == -5.2