Files
skills/tests/test_ci_tools.py
T
Kevin Veen-BirkenbachandClaude Opus 5.5 393803db3a perf(merge-fix): batch find_fix git calls and run -S in parallel slices
Almost all of find_fix's time went to git child processes: one merge-base per hit (2105 x 132 ms for a broad --grep), a single-threaded git log --all -S, and one branch --contains per printed candidate, run one after another. One rev-list HEAD set now decides in_head, -S runs as strided slices of rev-list --all through a thread pool and is sorted back into git log --all order, and the candidate lines are built in parallel. Output stays byte-identical on four real calls (3x to 142x faster). Tests pin the -S order and that the filters are alternatives.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-04 17:07:21 +01:00

137 lines
5.4 KiB
Python

"""Exercise ci_failures clustering and find_fix's ref search."""
from __future__ import annotations
import importlib.util
import shutil
import subprocess
import sys
import tempfile
import unittest
from pathlib import Path
REPO_ROOT = Path(__file__).resolve().parents[1]
CI_FAILURES = REPO_ROOT / "skills" / "ci-artifacts" / "scripts" / "ci_failures.py"
FIND_FIX = REPO_ROOT / "skills" / "merge-fix" / "scripts" / "find_fix.py"
def _load(path: Path):
spec = importlib.util.spec_from_file_location(path.stem, path)
module = importlib.util.module_from_spec(spec)
spec.loader.exec_module(module)
return module
class TestCiFailures(unittest.TestCase):
def setUp(self):
self.ci = _load(CI_FAILURES)
def test_jobs_differing_only_in_identifiers_share_a_cluster(self):
one = "2026-10-30T10:00:00.1Z setup ok\n##[error]Timeout on host 10.0.0.12 after 300s\n"
two = "\x1b[31m2026-10-30T11:00:00.1Z ##[error]Timeout on host 10.0.0.47 after 299s\x1b[0m\n"
other = "PLAY RECAP failed=0\nfatal: unable to reach registry\n"
groups = self.ci.cluster([("a", one), ("b", two), ("c", other)])
self.assertEqual(list(groups.values()), [["a", "b"], ["c"]])
def test_command_echo_and_retries_are_skipped_and_task_named(self):
text = (
'##[group]Run make deploy || echo "failed"\n'
"make deploy\n"
"##[endgroup]\n"
"FAILED - RETRYING: wait (3 retries left)\n"
"TASK [web-app-y : Probe] ****\n"
"Traceback (most recent call last): recovered on retry\n"
"TASK [web-app-x : Wait for health] ****\n"
'fatal: [localhost]: FAILED! => {"msg": "timeout 120"}\n'
"##[error]Process completed with exit code 2.\n"
)
self.assertEqual(
self.ci.signature(text),
'TASK [web-app-x : Wait for health] **** fatal: [localhost]: FAILED! => {"msg": "timeout <n>"}',
)
def test_lint_finding_beats_make_error_and_later_steps(self):
text = (
"Ran 41 tests in 1.0s\n"
"OK\n"
"UP017 [*] Use `datetime.UTC` alias\n"
" --> skills/democracy/scripts/council.py:92:40\n"
"Found 1 error.\n"
"make: *** [Makefile:15: test] Error 1\n"
"##[error]Process completed with exit code 2.\n"
"Post job cleanup.\n"
"SHA256 digest of uploaded artifact is 0123456789abcdef\n"
)
self.assertEqual(self.ci.signature(text), "UP<n> [*] Use `datetime.UTC` alias")
def test_generic_exit_code_line_is_not_the_signature(self):
text = "Error: disk full\n##[error]Process completed with exit code 1.\n"
self.assertEqual(self.ci.signature(text), "Error: disk full")
@unittest.skipUnless(shutil.which("git"), "git not installed")
class TestFindFix(unittest.TestCase):
def setUp(self):
self.tmp = tempfile.TemporaryDirectory()
self.addCleanup(self.tmp.cleanup)
self.repo = Path(self.tmp.name)
self.env = {
"PATH": "/usr/bin:/bin",
"HOME": str(self.repo),
"GIT_AUTHOR_NAME": "t",
"GIT_AUTHOR_EMAIL": "t@t",
"GIT_COMMITTER_NAME": "t",
"GIT_COMMITTER_EMAIL": "t@t",
}
self._git("init", "-q", "-b", "main")
self._git("commit", "-q", "--allow-empty", "-m", "fix: probe in head")
self._git("switch", "-q", "-c", "side")
self._git("commit", "-q", "--allow-empty", "-m", "fix: probe on side")
self._git("switch", "-q", "main")
def _git(self, *args: str) -> str:
return subprocess.run(
["git", *args], check=True, capture_output=True, text=True, env=self.env, cwd=self.repo
).stdout
def _find_fix(self, *args: str) -> list[str]:
result = subprocess.run(
[sys.executable, str(FIND_FIX), *args],
capture_output=True,
text=True,
check=True,
env=self.env,
cwd=self.repo,
)
return result.stdout.splitlines()
def _commit_on_side(self, name: str, text: str, message: str) -> None:
self._git("switch", "-q", "side")
(self.repo / name).write_text(text)
self._git("add", name)
self._git("commit", "-q", "-m", message)
self._git("switch", "-q", "main")
def test_only_commits_outside_head_are_candidates(self):
lines = self._find_fix("--grep", "probe")
self.assertEqual(lines[0], "hits=2 in_head=1 candidates=1")
self.assertIn("fix: probe on side", "\n".join(lines))
self.assertNotIn("probe in head", "\n".join(lines))
def test_pickaxe_lists_what_git_log_all_finds_in_its_order(self):
for step in range(12):
self._commit_on_side("probe.txt", "needle\n" * (step % 3), f"step {step}")
expected = self._git("log", "--all", "--format=%h %s", "-Sneedle").splitlines()
lines = self._find_fix("-S", "needle")
self.assertEqual(lines[0], f"hits={len(expected)} in_head=0 candidates={len(expected)}")
self.assertEqual([line.split("\t")[0] for line in lines[1:]], expected)
def test_filters_are_alternatives_not_narrowing(self):
self._commit_on_side("other.txt", "x\n", "chore: unrelated")
lines = self._find_fix("--grep", "probe", "--path", "other.txt")
self.assertEqual(lines[0], "hits=3 in_head=1 candidates=2")
if __name__ == "__main__":
unittest.main()