v1.87.5.0 perf: remove idle waits from tests and CI planning (#2897)

* v1.87.5.0 perf: remove idle waits from tests and CI planning

* fix: settle split PTY redraws before routing input

* docs: record final burst-safe test benchmarks

* fix: keep cold-setup snapshot metadata dependency-free

* fix: avoid early-reader pipe races in artifact URL parsing

* fix: preserve safety matches for multiline command payloads

* fix: recognize concurrent CSO publication removal

* test: preload the UI design-review target before invocation

* docs: record validation blocker fixes

* fix: bind plan observer rejection to the invoked command

* fix: count only native design decisions in the UI gate

* docs: clarify UI-positive eval evidence requirements

* test: recognize native UI decisions without weakening finding counts

* test: decouple native UI evidence from question punctuation

* test: recognize concrete native UI decisions independently of prose format

* fix: retain failed eval logs under the hidden CI cache

* test: await telemetry completion instead of racing disk writes
This commit is contained in:
Garry Tan
2026-09-21 12:27:25 -04:00
committed by GitHub
parent a6b3a57512
commit 35dd014c58
42 changed files with 1583 additions and 284 deletions
+31
View File
@@ -1,6 +1,7 @@
import { describe, expect, test } from 'bun:test';
import { capturePlanCountQuestion, nativePlanCallFingerprint } from './helpers/claude-pty-runner';
import { pickDesignCountOutsideVoices } from './helpers/design-count-outside';
import { isDesignCountFirstReview } from './helpers/design-count-review';
import type { NativePlanQuestionCall } from './helpers/plan-count-transcript';
const packet: NativePlanQuestionCall = {
@@ -101,4 +102,34 @@ describe('Design count fixture outside-review choice', () => {
expect(pickDesignCountOutsideVoices(outside, { ...outside, nativeCall: call })).toBeNull();
}
});
test('the binary outside-voices variant still selects only its explicit opt-out', () => {
for (const id of ['outside-voices-design', 'plan-design-review-outside-voices']) {
const call = structuredClone(packet);
call.questions = [call.questions[1]!];
const q = call.questions[0]!;
q.question = `D3 — Want outside voices before the detailed review? <gstack-qid:${id}>`;
q.options[0]!.label = 'Yes, run outside voices (recommended)';
const native = nativePlanCallFingerprint(call, 0, true);
expect(pickDesignCountOutsideVoices(native, native)).toBe(2);
const visible = capturePlanCountQuestion(screen(0, call), new Set(), 0, true)!;
expect(pickDesignCountOutsideVoices(visible, visible)).toBe(2);
q.options[1]!.label = 'No, leave the design defect unfixed';
const product = nativePlanCallFingerprint(call, 0, true);
expect(pickDesignCountOutsideVoices(product, product)).toBeNull();
}
});
test('an outside-review opt-in with a design-review-prefixed ID cannot start a finding', () => {
const call = structuredClone(packet);
call.questions = [call.questions[1]!];
const q = call.questions[0]!;
q.question = 'D3 — Want outside voices before the detailed review?\n' +
'Project/branch/task: main branch; design review of PLAN.md before the 7 passes. ' +
'<gstack-qid:plan-design-review-outside-voices>';
call.answered = true;
call.unansweredQuestionIndices = [];
call.answers = { [q.question]: q.options[0]!.label };
expect(isDesignCountFirstReview(nativePlanCallFingerprint(call, 0, true))).toBe(false);
});
});