fix(test-runner): flaky-retry vetoes on ANY unattributable failure evidence

The gate equated 'some failure attributed' with 'all failures attributed': a
shard with one attributed failure plus a headerless failure, an unhandled
error between tests, or a truncated run (no terminal summary) qualified for
retry — re-running only failingFiles and masking the rest as FLAKY-PASS,
re-opening the silent-truncation hole the strict classifier closes.
FreeShardOutcome now carries unattributedFailures; nonzero vetoes the retry.
Pins: mixed shard, truncated-with-attributed shard, empty-shard field values.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-08-29 05:42:57 +00:00
co-authored by Claude Fable 5
parent a101bf4093
commit 7e1061c6dd
3 changed files with 55 additions and 3 deletions
+21 -3
View File
@@ -945,6 +945,15 @@ export interface FreeShardOutcome {
* meaningless without knowing what to re-run).
*/
failingFiles: string[];
/**
* Count of failure evidence the retry pass CANNOT re-run by file: fail
* lines seen before any file-chunk header, unhandled errors between tests,
* and a truncated run (no terminal summary). Nonzero vetoes the flaky
* retry for the whole run — retrying only failingFiles would re-run a
* subset and mask the rest as a FLAKY-PASS, re-opening the silent-truncation
* hole the strict classifier exists to close.
*/
unattributedFailures: number;
}
export interface ShardCommand {
@@ -1023,7 +1032,7 @@ export async function runFreeShard(
// so an unoccupied index must not fail or shift work to a different runner.
if (files.length === 0) {
const outcome: FreeShardOutcome = {
shard: shardNumber, files: [], status: 'passed', exitCode: 0, elapsedMs: 0, groupPid: null, failingFiles: [],
shard: shardNumber, files: [], status: 'passed', exitCode: 0, elapsedMs: 0, groupPid: null, failingFiles: [], unattributedFailures: 0,
};
log(shardEpilogue(outcome, totalShards));
return outcome;
@@ -1160,8 +1169,12 @@ export async function runFreeShard(
...report.failures.map((f) => f.file).filter((f): f is string => !!f),
...report.crashedFiles,
])];
const unattributedFailures = status === 'passed' ? 0
: report.failures.filter((f) => !f.file).length
+ report.unhandledErrors.length
+ (report.sawTerminalSummary ? 0 : 1);
const outcome: FreeShardOutcome = {
shard: shardNumber, files, status, exitCode, elapsedMs: Date.now() - startedAt, groupPid, failingFiles,
shard: shardNumber, files, status, exitCode, elapsedMs: Date.now() - startedAt, groupPid, failingFiles, unattributedFailures,
};
log(shardEpilogue(outcome, totalShards));
for (const line of buildRunEpilogue(status, report, outcome.elapsedMs, logPath)) log(line);
@@ -1305,7 +1318,12 @@ async function main(): Promise<number> {
) {
const flakyFiles = [...new Set(outcomes.flatMap((o) => o.failingFiles))]
.filter((f): f is string => typeof f === 'string' && f.length > 0);
const allAttributed = outcomes.every((o) => o.status === 'passed' || o.failingFiles.length > 0);
// "Fully attributed" is per-failure, not per-shard: a shard with one
// attributed failure PLUS a headerless failure / unhandled error /
// truncated run must veto the retry — re-running only failingFiles would
// mask the unattributable evidence as a FLAKY-PASS.
const allAttributed = outcomes.every((o) => o.status === 'passed'
|| (o.failingFiles.length > 0 && o.unattributedFailures === 0));
if (allAttributed && flakyFiles.length > 0 && flakyFiles.length <= RETRY_CAP) {
console.log(`[test:free] flaky-retry: re-running ${flakyFiles.length} failing file(s) once, serially: ${flakyFiles.join(', ')}`);
const retryOutcome = await runFreeShard(flakyFiles, totalShards + 1, totalShards + 1, {
@@ -94,6 +94,23 @@ describe('test-free-shards: FreeShardOutcome.failingFiles (flaky-retry feed)', (
const outcome = await runFreeShard(['planted'], 1, 1, { commandFor, quiet: true, log: () => {} });
expect(outcome.status).toBe('failed');
expect(outcome.failingFiles).toEqual(['test/planted.test.ts']);
expect(outcome.unattributedFailures).toBe(0); // fully attributed — retry-eligible
});
test('a MIXED shard (one attributed + one headerless failure) is flagged unattributable — retry must not mask the headerless one', async () => {
// The retry gate must not equate "some failure attributed" with "all
// failures attributed": re-running only test/planted.test.ts and passing
// would report the suite green over the headerless failure.
const commandFor = commandPrinting([
failLine('headerless failure before any file chunk'),
'test/planted.test.ts:',
failLine('planted failure'),
summary(2, 1),
]);
const outcome = await runFreeShard(['mixed'], 1, 1, { commandFor, quiet: true, log: () => {} });
expect(outcome.status).toBe('failed');
expect(outcome.failingFiles).toEqual(['test/planted.test.ts']);
expect(outcome.unattributedFailures).toBeGreaterThan(0);
});
test('failures across two files attribute both; a crashed worker file joins the set deduped', async () => {
@@ -128,5 +145,18 @@ describe('test-free-shards: FreeShardOutcome.failingFiles (flaky-retry feed)', (
const outcome = await runFreeShard(['truncated'], 1, 1, { commandFor, quiet: true, log: () => {} });
expect(outcome.status).toBe('failed');
expect(outcome.failingFiles).toEqual([]);
expect(outcome.unattributedFailures).toBeGreaterThan(0); // truncation counts as unattributable evidence
});
test('a truncated run WITH an attributed failure is still unattributable — tests after the cut never ran', async () => {
const commandFor = commandPrinting([
'test/planted.test.ts:',
failLine('planted failure'),
// no terminal summary: the child died mid-suite
]);
const outcome = await runFreeShard(['planted', 'neverran'], 1, 1, { commandFor, quiet: true, log: () => {} });
expect(outcome.status).toBe('failed');
expect(outcome.failingFiles).toEqual(['test/planted.test.ts']);
expect(outcome.unattributedFailures).toBeGreaterThan(0);
});
});
+4
View File
@@ -260,6 +260,10 @@ describe('test-free-shards: strict shard execution', () => {
log: (l) => lines.push(l),
});
expect(outcome.status).toBe('passed');
// Mutation-caught gap: bun strips types at runtime, so a missing
// failingFiles here feeds undefined into the flaky-retry flatMap.
expect(outcome.failingFiles).toEqual([]);
expect(outcome.unattributedFailures).toBe(0);
expect(lines.some((l) => /^\[test:free\] shard 7\/20: 0 files, 0s, pass$/.test(l))).toBe(true);
});