Kevin Veen-BirkenbachandClaude Opus 5.5
0343a2f3ce
🧪 Test / 🧪 Lock + lint (push) Waiting to run
kvb-check-efficiency measures a change against its base: tokens.py counts skill text tokens and listing words, measure.py runs one command in a base worktree and the working tree (one run per side, the mean of five over 100, an estimate marked ~ when other processes load the CPU). kvb-check-speed reads wall time from the same run and is not relevant for skills. kvb-check-score prints fix, break, efficiency, speed and the product score with emojis plus a gate line: below 90/5 it reports, over 100 it requires asking the operator before the commit. Every skill that reported confidence and break risk now shows the score block; the 90/5 bar adds efficiency and speed at most 100. Commit blocks and the commit call's approval prompt name worktree, branch, diff stat and the score values, also for merges. 24 descriptions were shortened to keep the skill listing within its budget. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
105 lines
4.9 KiB
Python
105 lines
4.9 KiB
Python
"""Exercise score.py of kvb-check-score: formula, dash and new values, capping, every gate verdict and exit code."""
|
||
|
||
from __future__ import annotations
|
||
|
||
import subprocess
|
||
import sys
|
||
import unittest
|
||
from pathlib import Path
|
||
|
||
REPO_ROOT = Path(__file__).resolve().parents[1]
|
||
SCORE = REPO_ROOT / "skills" / "kvb-check-score" / "scripts" / "score.py"
|
||
PASS = "✅ gate: 90/5, efficiency and speed <= 100"
|
||
|
||
|
||
class TestScore(unittest.TestCase):
|
||
def _run(self, *args: str) -> subprocess.CompletedProcess:
|
||
return subprocess.run([sys.executable, str(SCORE), *args], capture_output=True, text=True, check=False)
|
||
|
||
def _score(self, fix: str, risk: str, efficiency: str, speed: str) -> tuple[list[str], int]:
|
||
result = self._run("--fix", fix, "--break", risk, "--efficiency", efficiency, "--speed", speed)
|
||
self.assertEqual(result.stderr, "")
|
||
return result.stdout.splitlines(), result.returncode
|
||
|
||
def test_formula_and_line_format(self):
|
||
self.assertEqual(
|
||
self._score("95", "4", "100", "100"),
|
||
(["🎯 fix 95 % · 💥 break 4 % · 🌱 efficiency 100 % · ⚡ speed 100 % · 🏆 score 91", PASS], 0),
|
||
)
|
||
lines, code = self._score("95", "2", "97", "-")
|
||
self.assertEqual(lines[0], "🎯 fix 95 % · 💥 break 2 % · 🌱 efficiency 97 % · ⚡ speed – · 🏆 score 96")
|
||
self.assertEqual(code, 0)
|
||
self.assertEqual(self._score("92.5", "0", "100", "100")[0][0].split(" · ")[0], "🎯 fix 92.5 %")
|
||
|
||
def test_dash_values_count_as_100(self):
|
||
self.assertEqual(
|
||
self._score("92", "3", "-", "-"),
|
||
(["🎯 fix 92 % · 💥 break 3 % · 🌱 efficiency – · ⚡ speed – · 🏆 score 89", PASS], 0),
|
||
)
|
||
|
||
def test_score_rounds_half_up(self):
|
||
for args, total in (
|
||
(("94.5", "0", "-", "-"), 95),
|
||
(("90", "5", "100", "100"), 86),
|
||
(("91", "5", "-", "-"), 86),
|
||
(("97", "0", "97", "-"), 100),
|
||
):
|
||
with self.subTest(args=args):
|
||
self.assertTrue(self._score(*args)[0][0].endswith(f"🏆 score {total}"))
|
||
|
||
def test_score_is_capped(self):
|
||
lines, code = self._score("100", "0", "50", "50")
|
||
self.assertTrue(lines[0].endswith("🏆 score 100"))
|
||
self.assertEqual((lines[1], code), (PASS, 0))
|
||
lines, code = self._score("0", "100", "-", "-")
|
||
self.assertTrue(lines[0].endswith("🏆 score 0"))
|
||
self.assertEqual(code, 1)
|
||
|
||
def test_boundaries_pass(self):
|
||
self.assertEqual(self._score("90", "5", "100", "100")[1], 0)
|
||
|
||
def test_90_5_failures_exit_1(self):
|
||
for args, verdict in (
|
||
(("89.5", "1", "-", "-"), "⛔ gate: fix 89.5 % < 90"),
|
||
(("95", "6", "-", "-"), "⛔ gate: break 6 % > 5"),
|
||
(("80", "10", "-", "-"), "⛔ gate: fix 80 % < 90, break 10 % > 5"),
|
||
(("85", "2", "150", "new"), "⛔ gate: fix 85 % < 90"),
|
||
):
|
||
with self.subTest(args=args):
|
||
lines, code = self._score(*args)
|
||
self.assertEqual((lines[1], code), (verdict, 1))
|
||
|
||
def test_cost_over_100_asks_the_operator_exit_3(self):
|
||
cases = {
|
||
("120", "100"): "⚠️ gate: efficiency 120 % > 100: ask the operator before the commit",
|
||
("-", "130"): "⚠️ gate: speed 130 % > 100: ask the operator before the commit",
|
||
("120", "130"): "⚠️ gate: efficiency 120 % > 100, speed 130 % > 100: ask the operator before the commit",
|
||
("100.5", "-"): "⚠️ gate: efficiency 100.5 % > 100: ask the operator before the commit",
|
||
("new", "-"): "⚠️ gate: efficiency new: ask the operator before the commit",
|
||
}
|
||
for (efficiency, speed), verdict in cases.items():
|
||
with self.subTest(efficiency=efficiency, speed=speed):
|
||
lines, code = self._score("95", "2", efficiency, speed)
|
||
self.assertEqual((lines[1], code), (verdict, 3))
|
||
|
||
def test_new_counts_as_100_in_the_score(self):
|
||
lines, _ = self._score("95", "0", "new", "-")
|
||
self.assertEqual(lines[0], "🎯 fix 95 % · 💥 break 0 % · 🌱 efficiency new · ⚡ speed – · 🏆 score 95")
|
||
|
||
def test_usage_errors_exit_2(self):
|
||
good = {"--fix": "95", "--break": "2", "--efficiency": "100", "--speed": "100"}
|
||
bad = (
|
||
("--fix", "101"), ("--fix", "-1"), ("--fix", "nan"), ("--break", "x"), ("--break", "-"),
|
||
("--efficiency", "0"), ("--efficiency", "-5"), ("--efficiency", "abc"), ("--speed", "inf"),
|
||
)
|
||
for flag, value in bad:
|
||
with self.subTest(flag=flag, value=value):
|
||
args = [item for key, val in {**good, flag: value}.items() for item in (key, val)]
|
||
result = self._run(*args)
|
||
self.assertEqual((result.returncode, result.stdout), (2, ""))
|
||
self.assertEqual(self._run("--fix", "95", "--break", "2", "--efficiency", "100").returncode, 2)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
unittest.main()
|