Skip to content

fix(stats): rename INCONCLUSIVE verdict to ERROR #1002

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
christso merged 2 commits into from
Apr 9, 2026
Merged

fix(stats): rename INCONCLUSIVE verdict to ERROR #1002

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0972754
fix(stats): rename INCONCLUSIVE verdict to ERROR
christso Apr 9, 2026
2b3f9d7
fix test: narrow ERROR assertion to RESULT: ERROR
christso Apr 9, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions apps/cli/src/commands/eval/statistics.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -220,9 +220,9 @@ export function formatEvaluationSummary(
let verdictColor: string;
let verdictText: string;
if (allExecutionErrors) {
overallVerdict = 'INCONCLUSIVE';
overallVerdict = 'ERROR';
verdictColor = '\x1b[33m'; // yellow
verdictText = `RESULT: INCONCLUSIVE (all ${summary.total} test(s) had execution errors — no evaluation was performed)`;
verdictText = `RESULT: ERROR (all ${summary.total} test(s) had execution errors — no evaluation was performed)`;
} else {
overallVerdict = overallPassed ? 'PASS' : 'FAIL';
verdictColor = overallPassed ? '\x1b[32m' : '\x1b[31m';
Expand Down
14 changes: 7 additions & 7 deletions apps/cli/test/commands/eval/statistics-inconclusive.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,8 +20,8 @@ function makeResult(overrides: Partial<EvaluationResult> = {}): EvaluationResult
};
}

describe('formatEvaluationSummary — inconclusive verdict', () => {
it('shows INCONCLUSIVE when all tests are execution errors', () => {
describe('formatEvaluationSummary — error verdict', () => {
it('shows ERROR when all tests are execution errors', () => {
const results = [
makeResult({
testId: 'err-1',
Expand All @@ -46,7 +46,7 @@ describe('formatEvaluationSummary — inconclusive verdict', () => {
const summary = calculateEvaluationSummary(results);
const output = formatEvaluationSummary(summary);

expect(output).toContain('RESULT: INCONCLUSIVE');
expect(output).toContain('RESULT: ERROR');
expect(output).toContain('all 3 test(s) had execution errors');
expect(output).toContain('no evaluation was performed');
});
Expand All @@ -65,9 +65,9 @@ describe('formatEvaluationSummary — inconclusive verdict', () => {
const summary = calculateEvaluationSummary(results);
const output = formatEvaluationSummary(summary);

// Should show PASS (the one graded test passed) not INCONCLUSIVE
// Should show PASS (the one graded test passed) not ERROR
expect(output).toContain('RESULT: PASS');
expect(output).not.toContain('INCONCLUSIVE');
expect(output).not.toContain('RESULT: ERROR');
});

it('shows FAIL when there are quality failures mixed with execution errors', () => {
Expand All @@ -85,7 +85,7 @@ describe('formatEvaluationSummary — inconclusive verdict', () => {
const output = formatEvaluationSummary(summary, { threshold: 0.8 });

expect(output).toContain('RESULT: FAIL');
expect(output).not.toContain('INCONCLUSIVE');
expect(output).not.toContain('RESULT: ERROR');
});

it('shows PASS when all tests pass and none are errors', () => {
Expand All @@ -98,6 +98,6 @@ describe('formatEvaluationSummary — inconclusive verdict', () => {
const output = formatEvaluationSummary(summary);

expect(output).toContain('RESULT: PASS');
expect(output).not.toContain('INCONCLUSIVE');
expect(output).not.toContain('RESULT: ERROR');
});
});
Loading