From 599a33f753f7f20e2ca951ae773642fcef0c58a2 Mon Sep 17 00:00:00 2001 From: bong-water-water-bong Date: Sat, 14 Nov 2026 07:00:12 -0400 Subject: [PATCH] pr_review_queue --duplicates: name the open PR pairs doing the same work Three pairs in one session on 2026-11-14, and nothing in the fleet noticed any of them until a reviewer had read both sides: engine#2418/#2419 both ADDED tools/ci/hip_f16_audit_pinned.py (two implementations of the same wrapper), and engine#2423/#2424 both changed the same single file os/mini/release-check.sh for the same issue. Two signals, both unambiguous: added-path two open PRs in one repo add the same NEW path same-files two open PRs whose changed-file sets are identical and <= 3 files Deliberately not a similarity score: #2420 and #2421 both touch CMakeLists.txt and are complementary (the ctest row and its runner), so a Jaccard threshold would have flagged a pair that had to land together. Its first run found a pair I had missed: site#15 and site#16 both ADD blog/2026-11-02-the-first-release.md -- main does not have that path, and the two versions differ by 67 lines. Reported on #16. Self-test classifies hand-built rows (no gh call: the classification is the logic) and pins the boundary that a 4-file PR is not paired by the small-set rule. --- tools/ci/pr_review_queue.py | 98 +++++++++++++++++++++++++++++++++++++ 1 file changed, 98 insertions(+) diff --git a/tools/ci/pr_review_queue.py b/tools/ci/pr_review_queue.py index c49b70143..554ac132f 100755 --- a/tools/ci/pr_review_queue.py +++ b/tools/ci/pr_review_queue.py @@ -298,17 +298,115 @@ def chk(want, got, what): return 0 +def duplicates(repos): + """Open PR pairs that are doing the same work, which cost a review round each to discover. + + Measured on 2026-11-14: three pairs in one session -- engine#2418/#2419 both ADDED + `tools/ci/hip_f16_audit_pinned.py` (two different implementations of the same wrapper), and + engine#2423/#2424 both changed the same single file `os/mini/release-check.sh` for the same issue. + Nothing in the fleet's tooling noticed either pair; the reviewer did, after reading both. + + Two signals, both cheap and both unambiguous: + + added-path two open PRs in one repo add the same NEW path -- the stronger one, because two + implementations of one new file cannot both land + same-files two open PRs whose changed-file sets are identical and small (<= 3 files each), + which is the "same one-file fix from two lanes" shape + + Deliberately not a similarity score over file sets: #2420 and #2421 both touch CMakeLists.txt and + are *complementary* (the row and its runner), so a Jaccard threshold would have flagged a pair + that had to land together. Only identical small sets and duplicated new paths are reported. + """ + rows = [] + for repo in repos: + prs = json.loads(gh(f'repos/{OWNER}/{repo}/pulls?state=open&per_page={PAGE}', paginate=True) or '[]') + per_pr = [] + for pr in prs: + if pr.get('draft'): + continue + files = json.loads(gh(f"repos/{OWNER}/{repo}/pulls/{pr['number']}/files?per_page={PAGE}", + paginate=True) or '[]') + paths = {f.get('filename') for f in files if f.get('filename')} + added = {f.get('filename') for f in files if f.get('status') == 'added' and f.get('filename')} + per_pr.append({'number': pr['number'], 'title': (pr.get('title') or '')[:60], + 'paths': paths, 'added': added}) + for i, left in enumerate(per_pr): + for right in per_pr[i + 1:]: + shared_added = sorted(left['added'] & right['added']) + if shared_added: + rows.append({'repo': repo, 'a': left['number'], 'b': right['number'], 'kind': 'added-path', + 'detail': shared_added[0], + 'a_title': left['title'], 'b_title': right['title']}) + elif (left['paths'] and left['paths'] == right['paths'] and len(left['paths']) <= 3): + rows.append({'repo': repo, 'a': left['number'], 'b': right['number'], 'kind': 'same-files', + 'detail': ', '.join(sorted(left['paths'])), + 'a_title': left['title'], 'b_title': right['title']}) + return rows + + +def self_test_duplicates(): + """The two signals, on hand-built rows -- no gh call, because the classification is the logic under test.""" + problems = [] + rows = [ + {'number': 1, 'title': 'a', 'paths': {'tools/x.py'}, 'added': {'tools/x.py'}}, + {'number': 2, 'title': 'b', 'paths': {'tools/x.py'}, 'added': {'tools/x.py'}}, + {'number': 3, 'title': 'c', 'paths': {'CMakeLists.txt'}, 'added': set()}, + {'number': 4, 'title': 'd', 'paths': {'CMakeLists.txt'}, 'added': set()}, + {'number': 5, 'title': 'e', 'paths': {'CMakeLists.txt', 'a.cc', 'b.cc', 'c.cc'}, 'added': set()}, + ] + + def classify(prs): + out = [] + for i, left in enumerate(prs): + for right in prs[i + 1:]: + shared = sorted(left['added'] & right['added']) + if shared: + out.append((left['number'], right['number'], 'added-path')) + elif left['paths'] and left['paths'] == right['paths'] and len(left['paths']) <= 3: + out.append((left['number'], right['number'], 'same-files')) + return out + + got = classify(rows) + if (1, 2, 'added-path') not in got: + problems.append(f"two PRs adding the same new path were not paired: {got}") + if (3, 4, 'same-files') not in got: + problems.append(f"two PRs with the same one-file set were not paired: {got}") + if any(pair[0] == 5 or pair[1] == 5 for pair in got): + problems.append(f"a 4-file PR was paired by the small-set rule: {got}") + if problems: + for problem in problems: + print('FAIL ' + problem) + return 1 + print('pr_review_queue --duplicates self-test: ok') + return 0 + + def main(argv): ap = argparse.ArgumentParser(description=__doc__.splitlines()[0]) ap.add_argument('--repos', nargs='+', default=list(DEFAULT_REPOS)) ap.add_argument('--min-age-hours', type=float, default=0.0) ap.add_argument('--json', action='store_true') ap.add_argument('--self-test', action='store_true') + ap.add_argument('--duplicates', action='store_true', + help='open PR pairs that add the same new path, or change the same small file set') ap.add_argument('--state', action='store_true', help='per open PR: the newest verdict object across reviews and comments') a = ap.parse_args(argv) if a.self_test: + if a.duplicates: + return self_test_duplicates() return self_test() if not a.state else self_test_state() + if a.duplicates: + rows = duplicates(a.repos) + if a.json: + print(json.dumps(rows, indent=1)) + return 0 + for row in rows: + print(f" {row['repo']:12} #{row['a']:<5} and #{row['b']:<5} both {row['kind']}: {row['detail']}") + print(f" {row['a_title']}") + print(f" {row['b_title']}") + print(f"pr_review_queue --duplicates: {len(rows)} pair(s) doing the same work") + return 0 if a.state: rows = state(a.repos) if a.json: