a5bf2ad59c
Aggregates all v0.2.0 sprint work (GARAA-30 through GARAA-40) and fixes 2 integration tests that broke when the codebase went async (DSPyLLMAdapter and full pipeline tests now properly await coroutines). 277 tests pass (260 unit + 17 integration). Co-Authored-By: Paperclip <noreply@paperclip.ing>
97 lines
3.4 KiB
Python
97 lines
3.4 KiB
Python
"""Additional unit tests for scoring edge cases."""
|
|
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
from prometheus.domain.entities import EvalResult, Trajectory
|
|
from prometheus.domain.scoring import normalize_score, should_accept
|
|
|
|
|
|
def _make_eval(scores: list[float]) -> EvalResult:
|
|
return EvalResult(
|
|
scores=scores,
|
|
feedbacks=[""] * len(scores),
|
|
trajectories=[
|
|
Trajectory(f"in{i}", f"out{i}", s, "", "p")
|
|
for i, s in enumerate(scores)
|
|
],
|
|
)
|
|
|
|
|
|
class TestShouldAcceptEdgeCases:
|
|
"""Extended edge-case tests for should_accept."""
|
|
|
|
def test_tiny_improvement_accepted(self) -> None:
|
|
old = _make_eval([0.5])
|
|
new = _make_eval([0.5001])
|
|
assert should_accept(old, new) is True
|
|
|
|
def test_tiny_improvement_below_threshold(self) -> None:
|
|
old = _make_eval([0.5])
|
|
new = _make_eval([0.5001])
|
|
assert should_accept(old, new, min_improvement=0.01) is False
|
|
|
|
def test_zero_scores_equal(self) -> None:
|
|
old = _make_eval([0.0, 0.0])
|
|
new = _make_eval([0.0, 0.0])
|
|
assert should_accept(old, new) is False
|
|
|
|
def test_negative_to_zero_not_accepted(self) -> None:
|
|
"""Scores should be [0,1] but test should_accept with edge values."""
|
|
old = _make_eval([-0.1])
|
|
new = _make_eval([0.0])
|
|
assert should_accept(old, new) is True
|
|
|
|
def test_large_improvement(self) -> None:
|
|
old = _make_eval([0.0, 0.0, 0.0])
|
|
new = _make_eval([1.0, 1.0, 1.0])
|
|
assert should_accept(old, new) is True
|
|
|
|
def test_single_score_improvement(self) -> None:
|
|
old = _make_eval([0.4])
|
|
new = _make_eval([0.5])
|
|
assert should_accept(old, new) is True
|
|
|
|
def test_min_improvement_exactly_met(self) -> None:
|
|
"""When improvement exactly equals min_improvement, still rejected (strict >)."""
|
|
old = _make_eval([0.5])
|
|
new = _make_eval([0.7])
|
|
assert should_accept(old, new, min_improvement=0.2) is False
|
|
|
|
def test_min_improvement_just_over(self) -> None:
|
|
old = _make_eval([0.5])
|
|
new = _make_eval([0.7001])
|
|
assert should_accept(old, new, min_improvement=0.2) is True
|
|
|
|
|
|
class TestNormalizeScoreEdgeCases:
|
|
"""Extended edge-case tests for normalize_score."""
|
|
|
|
def test_exact_bounds(self) -> None:
|
|
assert normalize_score(0.0) == 0.0
|
|
assert normalize_score(1.0) == 1.0
|
|
|
|
def test_very_large_value(self) -> None:
|
|
assert normalize_score(1e10) == 1.0
|
|
|
|
def test_very_negative_value(self) -> None:
|
|
assert normalize_score(-1e10) == 0.0
|
|
|
|
def test_custom_bounds_at_edges(self) -> None:
|
|
assert normalize_score(5.0, min_val=0.0, max_val=10.0) == 5.0
|
|
assert normalize_score(0.0, min_val=0.0, max_val=10.0) == 0.0
|
|
assert normalize_score(10.0, min_val=0.0, max_val=10.0) == 10.0
|
|
|
|
def test_negative_custom_range(self) -> None:
|
|
assert normalize_score(0.0, min_val=-5.0, max_val=5.0) == 0.0
|
|
assert normalize_score(-3.0, min_val=-5.0, max_val=5.0) == -3.0
|
|
assert normalize_score(-10.0, min_val=-5.0, max_val=5.0) == -5.0
|
|
|
|
def test_zero_span_range(self) -> None:
|
|
"""When min == max, clamps to min."""
|
|
assert normalize_score(5.0, min_val=5.0, max_val=5.0) == 5.0
|
|
assert normalize_score(0.0, min_val=5.0, max_val=5.0) == 5.0
|
|
|
|
def test_fractional_score(self) -> None:
|
|
assert normalize_score(0.3333) == pytest.approx(0.3333)
|