CalvinBackup/gstack
1
0 Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-10-31 22:14:25 +01:00
Code Issues Packages Projects Releases Wiki Activity

0.2: failureCauseOf takes the stall window instead of importing it; the PTY ledger never throws

Browse Source 
eval-store.ts imported STALL_WINDOW_MS from eval-budgets.ts, which free tests
replace with mock.module stubs (review-finalization-budget, office-hours,
qa-fix-loop, qa-only), so loading eval-store failed there. failureCauseOf is
now dependency-free: the record builders pass STALL_WINDOW_MS. A PTY session
whose handle cannot show its text (test doubles) records no panel instead of
throwing from runPtySession's cleanup. The 37186854666 replay also runs
through classifyTrialShard.
This commit is contained in:
garrytan committed 2026-10-04 18:14:21 +00:00
1 parent 30d2904c66
commit 694e970c65
5 files changed
+22 -11
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

scripts/lib/paid-report.ts
+2 -2
View File
@@ -28,7 +28,7 @@ import {
} from './shard-engine';
import { PAID_TEST_GLOBS, isPaidTestFile } from '../../test/helpers/paid-test-set';
import { CASE_CI_EXCLUDE, CASE_QUARANTINE, EVAL_POLICY, PERIODIC_CI_EXCLUDE } from '../../test/helpers/periodic-exclude-data';
import { FILE_RETRY_BUDGETS, STRICT_RETRY_CASE_BUDGETS } from '../../test/helpers/eval-budgets';
import { FILE_RETRY_BUDGETS, STALL_WINDOW_MS, STRICT_RETRY_CASE_BUDGETS } from '../../test/helpers/eval-budgets';
import {
getProjectEvalDir, getClaudeCliVersion, isFinalizedEvalResultFile, evalEntryOutcome, failureClassOf, panelVerdict,
sanitizeTrialError, formatTrialOutcomes, CONTRACT_VIOLATIONS_FILE, TRIAL_ENV, TRIAL_OUTCOME_SCHEMA, TRIAL_OUTCOMES_FILE,
@@ -305,7 +305,7 @@ export function junitCensus(manifest: PaidRunManifest, artifacts: ReportArtifact
const error = sanitizeTrialError(failedRecord?.error ?? failed?.message);
const sessions = caseSessions(ledger, id, byCase.size === 1);
const diagnosis = failed && failureClass ? trialFailureFields({ failure_class: failureClass, exit_reason: failedRecord?.exit_reason,
error: failedRecord?.error ?? failed.message, sessions, record: failedRecord }) : undefined;
error: failedRecord?.error ?? failed.message, sessions, record: failedRecord }, STALL_WINDOW_MS) : undefined;
if (failed) census.failedShards.add(key);
if (caseOutcome === 'skipped') {
bump(reasons, RUNTIME_SKIP_REASON);
scripts/test-paid-shards.ts
+2 -2
View File
@@ -78,7 +78,7 @@ import {
} from './lib/shard-engine';
import { PAID_TEST_GLOBS, isPaidTestFile } from '../test/helpers/paid-test-set';
import { CASE_CI_EXCLUDE, CASE_QUARANTINE, EVAL_POLICY, PERIODIC_CI_EXCLUDE } from '../test/helpers/periodic-exclude-data';
import { FILE_RETRY_BUDGETS, STRICT_RETRY_CASE_BUDGETS } from '../test/helpers/eval-budgets';
import { FILE_RETRY_BUDGETS, STALL_WINDOW_MS, STRICT_RETRY_CASE_BUDGETS } from '../test/helpers/eval-budgets';
import {
getProjectEvalDir, getClaudeCliVersion, isFinalizedEvalResultFile, evalEntryOutcome, failureClassOf, panelVerdict,
sanitizeTrialError, formatTrialOutcomes, CONTRACT_VIOLATIONS_FILE, TRIAL_ENV, TRIAL_OUTCOME_SCHEMA, TRIAL_OUTCOMES_FILE,
@@ -769,7 +769,7 @@ export function classifyTrialShard(
...(failedRecord?.exit_reason ? { exit_reason: String(failedRecord.exit_reason) } : {}),
...(Number.isInteger(failedRecord?.timeout_at_turn) ? { timeout_at_turn: failedRecord.timeout_at_turn } : {}),
...(sanitizeTrialError(raw) ? { error: sanitizeTrialError(raw) } : {}),
...trialFailureFields({ failure_class: cls, exit_reason: failedRecord?.exit_reason, error: raw, sessions: evidence.sessions, record: failedRecord }) };
...trialFailureFields({ failure_class: cls, exit_reason: failedRecord?.exit_reason, error: raw, sessions: evidence.sessions, record: failedRecord }, STALL_WINDOW_MS) };
};
if (outcome.runnerError !== undefined) return { ...base, harness: `runner error: ${sanitizeTrialError(outcome.runnerError) ?? 'unknown'}` };
if (outcome.status === 'never-started') return { ...base, harness: 'never started' };