You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit d062675
Browse filesBrowse the repository at this point in the historyBrowse files
fix(pm): board-snapshot — a blank listing page is not a reading
The Board Snapshot check went red on this PR (and on every scheduled
run since 2026-10-21, #24351) with a count-check SHORTFALL of the whole
board: the open walk's first listing page answered `200 []`, the tool
read it as the short page, declared the open set complete at zero
records, and compared zero with the board's own count.
Measured 2026-10-22: the issues listing answers blank to more than half
of the requests made to it (39 of 68 probes), each with its own request
id and its own count against the rate limit, so no cache is involved;
cache directives, a cache-busting query, sort, direction, page size,
state and since make no difference, and objectui and hotcrm answer the
same way. `/repos/{repo}`, the pulls listing and the per-number comment
pages never blanked.
So a blank listing page is asked again, same URL and page size, up to
`BLANK_PAGE_ASKS` (6) times, each ask a budgeted request and never a
sleep. A blank that survives the bound is acted on by where the walk is
(`blankPageStep`): past an anchor it is believed, because the cursor
does not advance and the next run re-reads from it; from the beginning
it is believed only if the board's own `open_issues_count`, read once as
the witness, is zero — otherwise the walk stops with its cursor
(`stopped_by: blank-listing`), nothing is marked complete, the count
check stays pending and the run exits 0 as a planned stop, which the
freshness row turns red if it becomes a streak. The manifest counts the
re-asks in `run.blank_pages_reasked`; the summary prints the count and
the stop. A new header section records the measurement.
Self-test: a new battery of 13 cases (the pure verdicts, the measured
failure healed on a fake board that blanks once, the bounded stop, the
anchored blank believed with its cursor unmoved), floor 12 -> 13, 169
cases. The PR leg's own arguments (`--dry-run --limit=5
--max-requests=25`) ran six times against the live board: six exits 0,
one of them a blank-listing stop and two after re-asks.
Claude-Session: https://claude.ai/code/session_01VCLHrrmPbwQHZcc2yqdFHD
Co-authored-by: Claude <noreply@anthropic.com>
stopped={kind: 'blank-listing',reason: `the ${key} listing answered EMPTY ${blankAsks} times from the beginning while the board reports ${witness??'an unknown number of'} open item(s)`};
1338
+
returnfalse;
1339
+
}
1340
+
}else{
1341
+
blankAsks=0;
1342
+
}
1255
1343
for(constrawofrows){
1256
1344
if(seen.has(raw.number))continue;
1257
1345
if(options.limit&&seen.size>=options.limit){
@@ -1439,6 +1527,7 @@ async function snapshot(repo, options) {
1439
1527
delta_ran: deltaRan,
1440
1528
delta_completed_here: deltaCompletedHere,
1441
1529
delta_requests: deltaRequests,
1530
+
blank_pages_reasked: blankPagesReasked,
1442
1531
},
1443
1532
});
1444
1533
@@ -1482,7 +1571,7 @@ export function renderRun(result, options) {
1482
1571
` open set ${openLine}`,
1483
1572
` delta ${deltaLine}`,
1484
1573
` since ${m.since??'(from the beginning)'} — ${m.since_reason}`,
1485
-
` read ${m.run.numbers_read} number(s) in ${m.requests} request(s); walk ${m.run.walk_complete ? 'complete' : 'INCOMPLETE'}`,
// -- the blank page ------------------------------------------------------
2591
+
battery('the blank page: asked again, then believed or stopped by where the walk is');
2592
+
constB=BLANK_PAGE_ASKS;
2593
+
t('below the bound a blank page is asked again — from the beginning of a board that reports open items',blankPageStep({asks: 1,since: null,page: 1,boardOpenItems: 118}).action==='ask-again');
2594
+
t('…and past an anchor alike',blankPageStep({asks: B-1,since: '2026-10-21T00:00:00Z',page: 1,boardOpenItems: null}).action==='ask-again');
2595
+
t('at the bound, past an anchor, it is believed — the cursor stays put and the next run re-reads from it',blankPageStep({asks: B,since: '2026-10-21T00:00:00Z',page: 1,boardOpenItems: 118}).action==='believe');
2596
+
t('…and on an offset page alike',blankPageStep({asks: B,since: null,page: 3,boardOpenItems: 118}).action==='believe');
2597
+
t('at the bound, from the BEGINNING of a board that reports open items, the walk STOPS — believing it would end a phase at zero records',blankPageStep({asks: B,since: null,page: 1,boardOpenItems: 118}).action==='stop');
2598
+
t('…and so does a board whose count is unknown: a blank is believed only where it can be true',blankPageStep({asks: B,since: null,page: 1,boardOpenItems: null}).action==='stop');
2599
+
t('…while a board that reports no open item can answer a blank first page, and is believed',blankPageStep({asks: B,since: null,page: 1,boardOpenItems: 0}).action==='believe');
t('THE MEASURED FAILURE, HEALED: a first listing that answers [] no longer ends the open phase at zero — the second ask sees the rows, the open set completes with every one of them and the count check reads OK',
t('a board that answers rows pays nothing, and past an anchor a blank that survives the bound is believed: the incremental walk completes with its cursor UNMOVED, so the next run re-reads from it',
0 commit comments