mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-16 18:05:31 +02:00
test: absorb the ponytail-import wave into the guard fixtures — ceilings, schema pin, triad phrasing
Skeleton ceilings re-captured for the 17 carved skills the wave deliberately
grew (reuse ladder + bounded closer + shortcut trail, net of the gated -236B
AUQ cut), each with its measured size in the comment per the carve-guards
protocol. eval-store schema pin updated to v2 (harvest gains
insertions/deletions/net). The AUQ prose-triad keeps its pinned per-choice
phrasing ('explicit on EACH choice') while still deferring the score scale to
the canonical Format rule — the shipped cut is strictly closer to the pre-cut
text than the render that already passed the NOT-WORSE gate. Autoplan carve
anchors follow the Phase 2.5 renumbering. Golden ship baselines re-captured.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Fable 5
parent
4c20eca33b
commit
76f38fcd0d
@@ -105,7 +105,7 @@ describe('EvalCollector', () => {
|
||||
const filepath = await collector.finalize();
|
||||
|
||||
const data: EvalResult = JSON.parse(fs.readFileSync(filepath, 'utf-8'));
|
||||
expect(data.schema_version).toBe(1);
|
||||
expect(data.schema_version).toBe(2);
|
||||
expect(data.tier).toBe('e2e');
|
||||
expect(data.total_tests).toBe(2);
|
||||
expect(data.passed).toBe(1);
|
||||
|
||||
Reference in New Issue
Block a user