refactor(skills)!: rename every skill to kvb-<category>-<name>
All 38 first-party skills move to kvb-<category>-<name> with the categories think, create, code, ci, git, check, org and skills; kvb-cleanup and kvb-help are the only uncategorized names. tests/test_naming.py pins the schema, the Agent Skills name rules and the README organigram. enable-plugins.js repoints hook commands of renamed skills in settings.local.json so a stale script path cannot block tools. BREAKING CHANGE: the old skill names and slash commands (/commit-next, /dream, /autotune, ...) are gone; use their kvb- successors listed in the README organigram. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Kevin Veen-BirkenbachandClaude Opus 5.5 committed
1 parent
64403cefca
commit
624baccfc4
59 files changed
+504
-312
No files matched your search
+170
@@ -0,0 +1,170 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Fetch the failed jobs of a GitHub Actions run and cluster them by error line.
|
||||
|
||||
Usage:
|
||||
ci_failures.py RUN_ID [--repo OWNER/REPO] [--out DIR] [--artifacts]
|
||||
|
||||
Prints how far HEAD moved since the run's commit, saves each finished failed
|
||||
job's log (colour stripped) under DIR (default /tmp/ci-logs-RUN_ID), and
|
||||
groups the jobs by the normalised error line that ended them (the last one). Jobs still running are
|
||||
listed but not fetched: their API log can stop hours early. The clustering is
|
||||
a heuristic; confirm a cluster's boundary against the logs.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import re
|
||||
import subprocess
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
FAILED = {"failure", "cancelled", "timed_out"}
|
||||
ANSI = re.compile(r"\x1b\[[0-9;]*[A-Za-z]")
|
||||
STAMP = re.compile(r"^\d{4}-\d\d-\d\dT[\d:.]+Z\s?")
|
||||
GENERIC = re.compile(r"failed=0\b|FAILED - RETRYING|^make(\[\d+\])?: \*\*\* \[.*\] Error \d+")
|
||||
PROCESS_END = re.compile(r"##\[error\]Process completed with exit code")
|
||||
ANNOTATION = re.compile(r"##\[error\]")
|
||||
FATAL = re.compile(r"fatal: \[|FAILED!|Traceback|AssertionError|panic:")
|
||||
LINT_AT = re.compile(r"\S+:\d+:\d+:? ((error|warning) )?[A-Z]{1,4}\d{3,4}\b")
|
||||
LINT_CODE = re.compile(r"^[A-Z]{1,4}\d{3,4}\b")
|
||||
LINT_ARROW = re.compile(r"^-->\s+\S+:\d+:\d+")
|
||||
SIGNAL = re.compile(r"\b(ERROR|Error|FAILED|FAIL|fatal|Exception|failed)\b")
|
||||
TASK = re.compile(r"^TASK \[")
|
||||
REFUSAL = "terminal escape sequences"
|
||||
|
||||
|
||||
def run(*cmd: str) -> subprocess.CompletedProcess:
|
||||
return subprocess.run(list(cmd), capture_output=True, text=True, check=False)
|
||||
|
||||
|
||||
def clean(line: str) -> str:
|
||||
return STAMP.sub("", ANSI.sub("", line)).strip()
|
||||
|
||||
|
||||
def normalise(line: str) -> str:
|
||||
line = re.sub(r"\b[0-9a-f]{7,}\b", "<hex>", line)
|
||||
line = re.sub(r"\d+", "<n>", line)
|
||||
return line[:200]
|
||||
|
||||
|
||||
def output_lines(text: str) -> list[tuple[str, str]]:
|
||||
kept, echo, task = [], False, ""
|
||||
for raw in text.splitlines():
|
||||
line = clean(raw)
|
||||
if PROCESS_END.search(line):
|
||||
break
|
||||
if line.startswith("##[group]Run "):
|
||||
echo = True
|
||||
elif line.startswith("##[endgroup]"):
|
||||
echo = False
|
||||
elif TASK.match(line):
|
||||
task = line
|
||||
elif line and not echo and not GENERIC.search(line):
|
||||
kept.append((task, line))
|
||||
return kept
|
||||
|
||||
|
||||
def is_lint(lines: list[tuple[str, str]], index: int) -> bool:
|
||||
line = lines[index][1]
|
||||
if LINT_AT.search(line):
|
||||
return True
|
||||
following = lines[index + 1][1] if index + 1 < len(lines) else ""
|
||||
return bool(LINT_CODE.match(line) and LINT_ARROW.match(following))
|
||||
|
||||
|
||||
def signature(text: str) -> str:
|
||||
lines = output_lines(text)
|
||||
tiers = (
|
||||
(lambda i: ANNOTATION.search(lines[i][1]), False),
|
||||
(lambda i: FATAL.search(lines[i][1]), True),
|
||||
(lambda i: is_lint(lines, i), False),
|
||||
(lambda i: SIGNAL.search(lines[i][1]), False),
|
||||
)
|
||||
for matches, with_task in tiers:
|
||||
for index in reversed(range(len(lines))):
|
||||
if matches(index):
|
||||
task, line = lines[index]
|
||||
found = ANNOTATION.sub("", line).strip()
|
||||
return normalise(f"{task} {found}" if with_task and task else found)
|
||||
return normalise(lines[-1][1]) if lines else "<empty log>"
|
||||
|
||||
|
||||
def cluster(jobs: list[tuple[str, str]]) -> dict[str, list[str]]:
|
||||
groups: dict[str, list[str]] = {}
|
||||
for job, text in jobs:
|
||||
groups.setdefault(signature(text), []).append(job)
|
||||
return dict(sorted(groups.items(), key=lambda item: -len(item[1])))
|
||||
|
||||
|
||||
def behind(sha: str) -> str:
|
||||
if run("git", "cat-file", "-e", f"{sha}^{{commit}}").returncode:
|
||||
return "behind=unknown (run commit not in this clone)"
|
||||
count = run("git", "rev-list", "--count", f"{sha}..HEAD").stdout.strip()
|
||||
moved = {p.split("/")[0] for p in run("git", "diff", "--name-only", f"{sha}..HEAD").stdout.split()}
|
||||
return f"behind={count} moved={','.join(sorted(moved)) or '-'}"
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser(prog="ci_failures")
|
||||
parser.add_argument("run_id")
|
||||
parser.add_argument("--repo")
|
||||
parser.add_argument("--out")
|
||||
parser.add_argument("--artifacts", action="store_true")
|
||||
args = parser.parse_args()
|
||||
repo = args.repo or run("gh", "repo", "view", "--json", "nameWithOwner", "-q", ".nameWithOwner").stdout.strip()
|
||||
if not repo:
|
||||
parser.error("no --repo and gh cannot resolve the current repository")
|
||||
meta = run("gh", "api", f"/repos/{repo}/actions/runs/{args.run_id}")
|
||||
# per_page=100 on a large matrix answers HTTP 502; 30 per page goes through.
|
||||
listing = run("gh", "api", "--paginate", f"/repos/{repo}/actions/runs/{args.run_id}/jobs?per_page=30",
|
||||
"--jq", ".jobs[] | {id, name, status, conclusion}")
|
||||
if meta.returncode or listing.returncode:
|
||||
print((meta.stderr or listing.stderr).strip(), file=sys.stderr)
|
||||
return 1
|
||||
data = json.loads(meta.stdout)
|
||||
jobs = [json.loads(line) for line in listing.stdout.splitlines() if line]
|
||||
out = Path(args.out or f"/tmp/ci-logs-{args.run_id}")
|
||||
out.mkdir(parents=True, exist_ok=True)
|
||||
print(f"run={args.run_id} repo={repo} head={data['head_sha'][:10]} status={data['status']} "
|
||||
f"jobs={len(jobs)} {behind(data['head_sha'])}")
|
||||
running = [j["name"] for j in jobs if j["status"] != "completed"]
|
||||
if running:
|
||||
print(f"running ({len(running)}, not fetched): {', '.join(running)}")
|
||||
fetched, missing = [], []
|
||||
for job in jobs:
|
||||
if job["status"] != "completed" or job["conclusion"] not in FAILED:
|
||||
continue
|
||||
log = run("gh", "api", "--allow-escape-sequences", f"/repos/{repo}/actions/jobs/{job['id']}/logs")
|
||||
if log.returncode or REFUSAL in log.stdout[:200]:
|
||||
missing.append(f"{job['conclusion']}\t{job['name']}\t{log.stderr.strip()[:80]}")
|
||||
continue
|
||||
slug = re.sub(r"[^A-Za-z0-9._-]+", "_", job["name"])[:80]
|
||||
path = out / f"{job['id']}-{slug}.log"
|
||||
path.write_text("\n".join(ANSI.sub("", line) for line in log.stdout.splitlines()), encoding="utf-8")
|
||||
text = "##[error]cancelled" if job["conclusion"] == "cancelled" else log.stdout
|
||||
fetched.append((f"{job['conclusion']}\t{job['name']}\t{path}", text))
|
||||
if missing:
|
||||
(out / "no-log.txt").write_text("\n".join(missing) + "\n", encoding="utf-8")
|
||||
counts = {c: sum(m.startswith(c) for m in missing) for c in FAILED}
|
||||
summary = ", ".join(f"{n} {c}" for c, n in sorted(counts.items()) if n)
|
||||
print(f"no log for {len(missing)} jobs ({summary}; never started or expired): {out / 'no-log.txt'}")
|
||||
for number, (sig, jobs) in enumerate(cluster(fetched).items(), 1):
|
||||
print(f"cluster {number} ({len(jobs)} jobs): {sig}")
|
||||
for job in jobs[:3]:
|
||||
print(f" {job}")
|
||||
if len(jobs) > 3:
|
||||
members = out / f"cluster-{number}.txt"
|
||||
members.write_text("\n".join(jobs) + "\n", encoding="utf-8")
|
||||
print(f" ... +{len(jobs) - 3} more: {members}")
|
||||
if args.artifacts:
|
||||
listing = run("gh", "api", f"/repos/{repo}/actions/runs/{args.run_id}/artifacts", "--paginate",
|
||||
"--jq", '.artifacts[] | "\\(.name)\\t\\(.size_in_bytes)"')
|
||||
print("artifacts:")
|
||||
print(listing.stdout.rstrip() or " none")
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
Reference in new issue
Block a user