Files
compounding-intelligence/scripts/test_pr_complexity_scorer.py
StepFun Agent 8374ec937e
Some checks failed
Test / pytest (pull_request) Failing after 8s
fix(perf-bottleneck): make find_slow_tests_pytest functional; unblock pytest collection
- find_slow_tests_pytest: actually run pytest with --durations and parse stdout
  instead of reading stale cache file. Now measures real test durations.
- test_pr_complexity_scorer.py: wrap module-level sys.exit() in
  if __name__ == "__main__" guard. This was crashing pytest collection
  entirely, making the repo un-testable and masking all other performance
  analysis.

Both issues were blocking the Performance Bottleneck Finder (#171) from
working. The script now successfully runs pytest, collects duration data,
and produces accurate reports.

Closes #171
2026-04-26 09:59:00 -04:00

172 lines
4.8 KiB
Python

#!/usr/bin/env python3
"""
Tests for PR Complexity Scorer — unit tests for the scoring logic.
"""
import sys
from pathlib import Path
sys.path.insert(0, str(Path(__file__).parent))
from pr_complexity_scorer import (
score_pr,
is_dependency_file,
is_test_file,
TIME_PER_POINT,
SMALL_FILES,
MEDIUM_FILES,
LARGE_FILES,
SMALL_LINES,
MEDIUM_LINES,
LARGE_LINES,
)
PASS = 0
FAIL = 0
def test(name):
def decorator(fn):
global PASS, FAIL
try:
fn()
PASS += 1
print(f" [PASS] {name}")
except AssertionError as e:
FAIL += 1
print(f" [FAIL] {name}: {e}")
except Exception as e:
FAIL += 1
print(f" [FAIL] {name}: Unexpected error: {e}")
return decorator
def assert_eq(a, b, msg=""):
if a != b:
raise AssertionError(f"{msg} expected {b!r}, got {a!r}")
def assert_true(v, msg=""):
if not v:
raise AssertionError(msg or "Expected True")
def assert_false(v, msg=""):
if v:
raise AssertionError(msg or "Expected False")
print("=== PR Complexity Scorer Tests ===\n")
print("-- File Classification --")
@test("dependency file detection — requirements.txt")
def _():
assert_true(is_dependency_file("requirements.txt"))
assert_true(is_dependency_file("src/requirements.txt"))
assert_false(is_dependency_file("requirements_test.txt"))
@test("dependency file detection — pyproject.toml")
def _():
assert_true(is_dependency_file("pyproject.toml"))
assert_false(is_dependency_file("myproject.py"))
@test("test file detection — pytest style")
def _():
assert_true(is_test_file("tests/test_api.py"))
assert_true(is_test_file("test_module.py"))
assert_true(is_test_file("src/module_test.py"))
@test("test file detection — other frameworks")
def _():
assert_true(is_test_file("spec/feature_spec.rb"))
assert_true(is_test_file("__tests__/component.test.js"))
assert_false(is_test_file("testfixtures/helper.py"))
print("\n-- Scoring Logic --")
@test("small PR gets low score (1-3)")
def _():
score, minutes, _ = score_pr(
files_changed=3,
additions=50,
deletions=10,
has_dependency_changes=False,
test_coverage_delta=None
)
assert_true(1 <= score <= 3, f"Score should be low, got {score}")
assert_true(minutes < 20)
@test("medium PR gets medium score (4-6)")
def _():
score, minutes, _ = score_pr(
files_changed=15,
additions=400,
deletions=100,
has_dependency_changes=False,
test_coverage_delta=None
)
assert_true(4 <= score <= 6, f"Score should be medium, got {score}")
assert_true(20 <= minutes <= 45)
@test("large PR gets high score (7-9)")
def _():
score, minutes, _ = score_pr(
files_changed=60,
additions=3000,
deletions=1500,
has_dependency_changes=True,
test_coverage_delta=None
)
assert_true(7 <= score <= 9, f"Score should be high, got {score}")
assert_true(minutes >= 45)
@test("dependency changes boost score")
def _():
base_score, _, _ = score_pr(
files_changed=10, additions=200, deletions=50,
has_dependency_changes=False, test_coverage_delta=None
)
dep_score, _, _ = score_pr(
files_changed=10, additions=200, deletions=50,
has_dependency_changes=True, test_coverage_delta=None
)
assert_true(dep_score > base_score, f"Deps: {base_score} -> {dep_score}")
@test("adding tests lowers complexity")
def _():
base_score, _, _ = score_pr(
files_changed=8, additions=150, deletions=20,
has_dependency_changes=False, test_coverage_delta=None
)
better_score, _, _ = score_pr(
files_changed=8, additions=180, deletions=20,
has_dependency_changes=False, test_coverage_delta=3
)
assert_true(better_score < base_score, f"Tests: {base_score} -> {better_score}")
@test("removing tests increases complexity")
def _():
base_score, _, _ = score_pr(
files_changed=8, additions=150, deletions=20,
has_dependency_changes=False, test_coverage_delta=None
)
worse_score, _, _ = score_pr(
files_changed=8, additions=150, deletions=20,
has_dependency_changes=False, test_coverage_delta=-2
)
assert_true(worse_score > base_score, f"Remove tests: {base_score} -> {worse_score}")
@test("score bounded 1-10")
def _():
for files, adds, dels in [(1, 10, 5), (100, 10000, 5000)]:
score, _, _ = score_pr(files, adds, dels, False, None)
assert_true(1 <= score <= 10, f"Score {score} out of range")
@test("estimated minutes exist for all scores")
def _():
for s in range(1, 11):
assert_true(s in TIME_PER_POINT, f"Missing time for score {s}")
if __name__ == "__main__":
print(f"\n=== Results: {PASS} passed, {FAIL} failed ===")
sys.exit(0 if FAIL == 0 else 1)