RomanNum3ral
/
gstack
mirror of https://github.com/garrytan/gstack.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix: triage E2E runs both test files in subprocesses 

Add assertions verifying both math.test.js (pre-existing failure) and
string.test.js (in-branch failure) actually executed during triage.
Prevents false passes where only one failure class is exercised.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan 2026-03-21 10:05:27 -07:00
parent 700e024a4a
commit 51bd9a5a63
No known key found for this signature in database
GPG Key ID: C1F69E85C74EFE1D
1 changed files with 11 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
test/skill-e2e.test.ts
View File

@ -3092,12 +3092,20 @@ This is a solo repo (REPO_MODE=solo). For pre-existing failures, recommend fixin
console.log(`Mentions truncate/string (in-branch bug): ${mentionsTruncate}`); console.log(`Mentions truncate/string (in-branch bug): ${mentionsTruncate}`);
console.log(`Mentions divide/math (pre-existing bug): ${mentionsDivide}`); console.log(`Mentions divide/math (pre-existing bug): ${mentionsDivide}`);
// Verify BOTH failure classes are exercised (not just detected):
// The test runner must have actually run both test files
const ranMathTest = output.includes('math.test') || output.includes('FAIL: divide');
const ranStringTest = output.includes('string.test') || output.includes('FAIL: truncate');
console.log(`Ran math test file (pre-existing failure): ${ranMathTest}`);
console.log(`Ran string test file (in-branch failure): ${ranStringTest}`);
recordE2E('/ship triage', 'Test Failure Triage E2E', result, { recordE2E('/ship triage', 'Test Failure Triage E2E', result, {
passed: result.exitReason === 'success' && hasInBranch && hasPreExisting, passed: result.exitReason === 'success' && hasInBranch && hasPreExisting,
has_in_branch_classification: hasInBranch, has_in_branch_classification: hasInBranch,
has_pre_existing_classification: hasPreExisting, has_pre_existing_classification: hasPreExisting,
mentions_truncate: mentionsTruncate, mentions_truncate: mentionsTruncate,
mentions_divide: mentionsDivide, mentions_divide: mentionsDivide,
ran_both_test_files: ranMathTest && ranStringTest,
}); });
expect(result.exitReason).toBe('success'); expect(result.exitReason).toBe('success');
@ -3107,6 +3115,9 @@ This is a solo repo (REPO_MODE=solo). For pre-existing failures, recommend fixin
// Must mention the specific bugs // Must mention the specific bugs
expect(mentionsTruncate).toBe(true); expect(mentionsTruncate).toBe(true);
expect(mentionsDivide).toBe(true); expect(mentionsDivide).toBe(true);
// Must have actually run both test files (exercises both failure classes)
expect(ranMathTest).toBe(true);
expect(ranStringTest).toBe(true);
}, 240_000); }, 240_000);
}); });