mirror of
https://github.com/huggingface/transformers.git
synced 2026-10-29 01:06:24 +08:00
d0e91c7ff1
* use a single function for GH calls * check token before loop * Add pre-flight token/quota check and per-request rate-limit logging to github_utils - Add _log_token_status(): calls /rate_limit once before the retry loop (no quota consumed). Fails immediately if: CI env with no token, token rejected (401), or quota already exhausted (remaining=0). 401 with vs. without token gives distinct actionable error messages. - Add _log_rate_limit_headers(): prints limit/used/remaining/reset on every request attempt, labeled [initial] / [retry N/M]. Skipped on 401 (GitHub omits those headers on auth failures). - Remove _is_expired_or_bad_token(): pre-flight check catches bad tokens earlier; 401s in the retry loop fall through to the generic fail-hard with the raw body. - Update tests: remove IsExpiredOrBadTokenTest (function deleted), add LogTokenStatusTest covering all _log_token_status failure modes, patch _log_token_status in GithubRequestTest.setUp so mock responses are not consumed by the pre-flight call. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * Fix stale comments about get_github_json error handling get_github_json now raises RuntimeError on error responses (rate limiting, auth failures, etc.) rather than returning an error dict. Update comments in notification_service.py and check_bad_commit.py that incorrectly described the old behaviour, while keeping the defensive .get() calls which guard against unexpected response shapes. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * format * fix --------- Co-authored-by: ydshieh <ydshieh@users.noreply.github.com> Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
70 lines
2.0 KiB
Python
70 lines
2.0 KiB
Python
import argparse
|
|
import math
|
|
import time
|
|
import traceback
|
|
|
|
import dateutil.parser as date_parser
|
|
from github_utils import get_github_json
|
|
|
|
|
|
def extract_time_from_single_job(job):
|
|
"""Extract time info from a single job in a GitHub Actions workflow run"""
|
|
|
|
job_info = {}
|
|
|
|
start = job["started_at"]
|
|
end = job["completed_at"]
|
|
|
|
start_datetime = date_parser.parse(start)
|
|
end_datetime = date_parser.parse(end)
|
|
|
|
duration_in_min = round((end_datetime - start_datetime).total_seconds() / 60.0)
|
|
|
|
job_info["started_at"] = start
|
|
job_info["completed_at"] = end
|
|
job_info["duration"] = duration_in_min
|
|
|
|
return job_info
|
|
|
|
|
|
def get_job_time(workflow_run_id, token=None):
|
|
"""Extract time info for all jobs in a GitHub Actions workflow run"""
|
|
|
|
url = f"https://api.github.com/repos/huggingface/transformers/actions/runs/{workflow_run_id}/jobs?per_page=50"
|
|
result = get_github_json(url, token=token)
|
|
job_time = {}
|
|
|
|
try:
|
|
job_time.update({job["name"]: extract_time_from_single_job(job) for job in result["jobs"]})
|
|
pages_to_iterate_over = math.ceil((result["total_count"] - 50) / 50)
|
|
|
|
for i in range(pages_to_iterate_over):
|
|
time.sleep(1)
|
|
result = get_github_json(url + f"&page={i + 2}", token=token)
|
|
job_time.update({job["name"]: extract_time_from_single_job(job) for job in result["jobs"]})
|
|
|
|
return job_time
|
|
except Exception:
|
|
print(f"Unknown error, could not fetch links:\n{traceback.format_exc()}")
|
|
|
|
return {}
|
|
|
|
|
|
if __name__ == "__main__":
|
|
r"""
|
|
Example:
|
|
|
|
python get_github_job_time.py --workflow_run_id 2945609517
|
|
"""
|
|
|
|
parser = argparse.ArgumentParser()
|
|
# Required parameters
|
|
parser.add_argument("--workflow_run_id", type=str, required=True, help="A GitHub Actions workflow run id.")
|
|
args = parser.parse_args()
|
|
|
|
job_time = get_job_time(args.workflow_run_id)
|
|
job_time = dict(sorted(job_time.items(), key=lambda item: item[1]["duration"], reverse=True))
|
|
|
|
for k, v in job_time.items():
|
|
print(f"{k}: {v['duration']}")
|