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
+4 -4
View File
@@ -61,9 +61,9 @@ describe('evals.yml sliced-lane wiring (post-matrix)', () => {
});
test('planner, executors, and report all run tier=gate on the shared runner', () => {
expect(evalsYml).toMatch(/EVALS_TIER=gate bun run scripts\/test-paid-shards\.ts --tier gate --emit-plan/);
expect(evalsYml).toMatch(/EVALS_TIER=gate bun --no-install run scripts\/test-paid-shards\.ts --tier gate --emit-plan/);
expect(evalsYml).toMatch(/EVALS_TIER=gate bun run scripts\/test-paid-shards\.ts --tier gate --plan .* --slice /);
expect(evalsYml).toMatch(/EVALS_TIER=gate bun run scripts\/test-paid-shards\.ts --tier gate --report /);
expect(evalsYml).toMatch(/EVALS_TIER=gate bun --no-install run scripts\/test-paid-shards\.ts --tier gate --report /);
});
test('executor matrix slice list matches the planner --slices count', () => {
@@ -124,9 +124,9 @@ describe('evals.yml sliced-lane wiring (post-matrix)', () => {
describe('evals-periodic.yml sliced-lane wiring', () => {
test('planner/executor/report tier=periodic and slice counts agree', () => {
expect(periodicYml).toMatch(/EVALS_TIER=periodic bun run scripts\/test-paid-shards\.ts --tier periodic --emit-plan/);
expect(periodicYml).toMatch(/EVALS_TIER=periodic bun --no-install run scripts\/test-paid-shards\.ts --tier periodic --emit-plan/);
expect(periodicYml).toMatch(/EVALS_TIER=periodic bun run scripts\/test-paid-shards\.ts --tier periodic --plan .* --slice /);
expect(periodicYml).toMatch(/EVALS_TIER=periodic bun run scripts\/test-paid-shards\.ts --tier periodic --report /);
expect(periodicYml).toMatch(/EVALS_TIER=periodic bun --no-install run scripts\/test-paid-shards\.ts --tier periodic --report /);
const planned = plannedSlices(periodicYml);
const matrices = matrixSlices(periodicYml);
expect(planned).toHaveLength(1);