Merge origin/main (v1.91.9.0, #2998) into capy/audit-fix-wave; release as v1.91.10.0

Main shipped v1.91.9.0, so this wave becomes v1.91.10.0. Conflicts kept this
branch's planner-derived assertions. Main's new test-value eval gets rule
kinds for its three gate cases and its measured 332 s duration from #2998's
CI; census counts and the PR fallback floor follow the new file. The packing
test now weighs each tier's recorded durations the way the planner does.
This commit is contained in:
garrytan committed 2026-09-29 22:00:14 +00:00
commit 58b5e3f977
58 files changed
+2453 -220

No files matched your search

+10
View File
@@ -783,6 +783,10 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
"test/fixtures/coverage-diagram-legend-as.json",
'test/helpers/coverage-audit.ts', 'test/helpers/office-hours-attempt.ts'
],
// Test value bar behavior (weak paths, low-value findings, report-only sweep)
'ship-coverage-value': ['ship/**', 'scripts/resolvers/testing.ts', 'test/fixtures/coverage-audit-fixture.ts', 'test/skill-e2e-test-value.test.ts', 'test/helpers/test-value-fixture.ts', 'scripts/resolvers/test-value.ts', 'test/helpers/office-hours-attempt.ts', 'lib/eval-model.ts'],
'review-test-value': ['review/**', 'test/fixtures/coverage-audit-fixture.ts', 'test/skill-e2e-test-value.test.ts', 'test/helpers/test-value-fixture.ts', 'scripts/resolvers/test-value.ts', 'test/helpers/office-hours-attempt.ts', 'lib/eval-model.ts'],
'test-audit-report-only': ['test-audit/**', 'test/fixtures/coverage-audit-fixture.ts', 'test/skill-e2e-test-value.test.ts', 'test/helpers/test-value-fixture.ts', 'scripts/resolvers/test-value.ts', 'test/helpers/office-hours-attempt.ts', 'lib/eval-model.ts'],
'plan-eng-coverage-audit': [
'scripts/resolvers/learnings.ts',
'test/fixtures/coverage-audit-ci-diagrams.json',
@@ -1231,6 +1235,9 @@ export const E2E_TIERS: Record<string, 'gate' | 'periodic' | 'marathon'> = {
'plan-eng-review': 'periodic',
'plan-eng-review-artifact': 'periodic',
'plan-eng-coverage-audit': 'gate',
'ship-coverage-value': 'gate',
'review-test-value': 'gate',
'test-audit-report-only': 'gate',
'plan-review-report': 'gate',
// Plan-mode handshake. plan-ceo/plan-devex ask-first reliably (gate-tier);
@@ -1664,6 +1671,9 @@ export const E2E_KINDS: Record<string, 'rule' | 'behavior' | 'judge'> = {
'plan-ceo-review-plan-mode': 'rule',
'plan-eng-review-plan-mode': 'rule',
'plan-design-review-plan-mode': 'rule',
'ship-coverage-value': 'rule',
'review-test-value': 'rule',
'test-audit-report-only': 'rule',
'plan-devex-review-plan-mode': 'rule',
'plan-mode-no-op': 'rule',
'office-hours-auto-mode': 'rule',