Files
gstack/scripts/paid-test-durations.json
T
garrytan d5876efa5d chore(evals): refresh paid duration seeds from proof runs 36597762183 and 36606688266
Both tiers, merged in run order (the later run wins). Notable: split-overflow
1332s -> 504s, section-loading 604s -> 342s, mode-routing 575s -> 444s;
multi-finding-batching 734s -> 1318s (its red path in run 36606688266).
2026-09-29 19:30:43 +00:00

202 lines
12 KiB
JSON

{
"version": 2,
"recordedAt": "2026-09-29T19:29:33.835Z",
"tiers": {
"gate": {
"test/llm-judge-recommendation.test.ts": 1000,
"test/skill-e2e-ask-user-question-format-compliance.test.ts": 63904,
"test/skill-e2e-autoplan-dual-voice.test.ts": 1000,
"test/skill-e2e-bws.test.ts": 101092,
"test/skill-e2e-context-skills.test.ts": 1000,
"test/skill-e2e-coverage-audit.test.ts": 50849,
"test/skill-e2e-cso.test.ts": 227394,
"test/skill-e2e-deploy.test.ts": 423978,
"test/skill-e2e-design.test.ts": 261000,
"test/skill-e2e-design.test.ts#design-review-detector-shim": 42811,
"test/skill-e2e-design.test.ts#design-review-detector-shim-dom": 81914,
"test/skill-e2e-design.test.ts#design-review-plugin-handoff": 126642,
"test/skill-e2e-design.test.ts#plan-design-review-no-ui-scope": 24431,
"test/skill-e2e-diagram.test.ts": 29998,
"test/skill-e2e-docsync-spawned.test.ts": 137929,
"test/skill-e2e-first-task-scaffold.test.ts": 1000,
"test/skill-e2e-gbrain-roundtrip-local.test.ts": 1000,
"test/skill-e2e-hermetic-canary.test.ts": 8813,
"test/skill-e2e-investigate-owned-completion.test.ts": 45178,
"test/skill-e2e-investigate-owned-termination.test.ts": 48608,
"test/skill-e2e-ios-device.test.ts": 1000,
"test/skill-e2e-learnings.test.ts": 28899,
"test/skill-e2e-office-hours-auto-mode.test.ts": 83101,
"test/skill-e2e-office-hours-brain-writeback.test.ts": 1000,
"test/skill-e2e-office-hours-phase4.test.ts": 1000,
"test/skill-e2e-office-hours.test.ts": 1000,
"test/skill-e2e-plan-ceo-finding-floor.test.ts": 297738,
"test/skill-e2e-plan-ceo-plan-mode.test.ts": 36812,
"test/skill-e2e-plan-decision-classification.test.ts": 1000,
"test/skill-e2e-plan-design-with-ui.test.ts": 595151,
"test/skill-e2e-plan-devex-finding-floor.test.ts": 207635,
"test/skill-e2e-plan-devex-peer-comparison-classification.test.ts": 1000,
"test/skill-e2e-plan-devex-plan-mode.test.ts": 115679,
"test/skill-e2e-plan-format.test.ts": 1000,
"test/skill-e2e-plan-mode-no-op.test.ts": 217184,
"test/skill-e2e-plan-prosons.test.ts": 1000,
"test/skill-e2e-plan-tune.test.ts": 63925,
"test/skill-e2e-plan.test.ts": 251000,
"test/skill-e2e-plan.test.ts#codex-offered-ceo-review": 49880,
"test/skill-e2e-plan.test.ts#codex-offered-design-review": 54895,
"test/skill-e2e-plan.test.ts#codex-offered-eng-review": 59818,
"test/skill-e2e-plan.test.ts#codex-offered-office-hours": 50442,
"test/skill-e2e-plan.test.ts#office-hours-spec-review": 33866,
"test/skill-e2e-plan.test.ts#plan-ceo-review-benefits": 48811,
"test/skill-e2e-plan.test.ts#plan-review-report": 76406,
"test/skill-e2e-qa-bugs.test.ts": 1000,
"test/skill-e2e-qa-callers.test.ts": 737164,
"test/skill-e2e-qa-functional-fix.test.ts": 235133,
"test/skill-e2e-qa-functional.test.ts": 356641,
"test/skill-e2e-qa-workflow.test.ts": 427303,
"test/skill-e2e-retro.test.ts": 141804,
"test/skill-e2e-review-army.test.ts": 520000,
"test/skill-e2e-review-army.test.ts#review-army-delivery-audit": 50219,
"test/skill-e2e-review-army.test.ts#review-army-json-findings": 21332,
"test/skill-e2e-review-army.test.ts#review-army-migration-safety": 145112,
"test/skill-e2e-review-army.test.ts#review-army-perf-n-plus-one": 241299,
"test/skill-e2e-review-army.test.ts#review-army-quality-score": 86836,
"test/skill-e2e-review-attribution.test.ts": 77592,
"test/skill-e2e-review.test.ts": 136132,
"test/skill-e2e-session-intelligence.test.ts": 55332,
"test/skill-e2e-shared-libs-paths.test.ts": 680000,
"test/skill-e2e-shared-libs-paths.test.ts#shared-libs-review-index-flags": 190202,
"test/skill-e2e-shared-libs-paths.test.ts#shared-libs-review-path-eligibility": 205615,
"test/skill-e2e-shared-libs-paths.test.ts#shared-libs-review-prior-coverage": 214728,
"test/skill-e2e-shared-libs.test.ts": 658000,
"test/skill-e2e-shared-libs.test.ts#shared-libs-read-only": 197454,
"test/skill-e2e-shared-libs.test.ts#shared-libs-review-lifecycle": 267080,
"test/skill-e2e-shared-libs.test.ts#shared-libs-review-revalidation": 316752,
"test/skill-e2e-shared-libs.test.ts#shared-libs-unsupported-git": 170776,
"test/skill-e2e-ship-docsync.test.ts": 129000,
"test/skill-e2e-ship-docsync.test.ts#ship-docsync-completion": 366116,
"test/skill-e2e-ship-docsync.test.ts#ship-docsync-current": 434135,
"test/skill-e2e-ship-docsync.test.ts#ship-docsync-failure": 164667,
"test/skill-e2e-ship-docsync.test.ts#ship-docsync-late-result": 214218,
"test/skill-e2e-ship-docsync.test.ts#ship-docsync-launch-failure": 140987,
"test/skill-e2e-ship-docsync.test.ts#ship-docsync-missing-asset": 142564,
"test/skill-e2e-ship-docsync.test.ts#ship-docsync-missing-marker": 117648,
"test/skill-e2e-ship-docsync.test.ts#ship-docsync-recovery": 225432,
"test/skill-e2e-ship-docsync.test.ts#ship-docsync-stale-after": 269572,
"test/skill-e2e-ship-docsync.test.ts#ship-docsync-stale-before": 197633,
"test/skill-e2e-ship-docsync.test.ts#ship-docsync-store": 396588,
"test/skill-e2e-ship-docsync.test.ts#ship-docsync-timeout-unsettled": 152278,
"test/skill-e2e-ship-hook-consent.test.ts": 69995,
"test/skill-e2e-ship-hook-refresh.test.ts": 70007,
"test/skill-e2e-ship-skip.test.ts": 80318,
"test/skill-e2e-skillify.test.ts": 191127,
"test/skill-e2e-third-party-actions.test.ts": 82102,
"test/skill-e2e-triage.test.ts": 54088,
"test/skill-e2e-workflow.test.ts": 184925,
"test/skill-llm-eval.test.ts": 354000,
"test/skill-routing-e2e.test.ts": 1000
},
"periodic": {
"test/carve-section-loading-browse.test.ts": 92911,
"test/carve-section-loading-codex.test.ts": 150172,
"test/carve-section-loading-design-consultation.test.ts": 318385,
"test/carve-section-loading-design-html.test.ts": 245660,
"test/carve-section-loading-design-shotgun.test.ts": 140298,
"test/carve-section-loading-document-release.test.ts": 97810,
"test/carve-section-loading-land-and-deploy.test.ts": 156293,
"test/carve-section-loading-plan-design-review.test.ts": 223606,
"test/carve-section-loading-plan-devex-review.test.ts": 384295,
"test/carve-section-loading-plan-eng-review.test.ts": 297627,
"test/carve-section-loading-qa.test.ts": 149637,
"test/carve-section-loading-retro.test.ts": 199931,
"test/carve-section-loading-review.test.ts": 247902,
"test/carve-section-loading-setup-gbrain.test.ts": 80994,
"test/carve-section-loading-spec.test.ts": 176639,
"test/codex-e2e-recommendation-substance.test.ts": 1000,
"test/codex-e2e-shared-libs.test.ts": 1000,
"test/codex-e2e-sol-scope.test.ts": 1000,
"test/codex-e2e.test.ts": 1000,
"test/llm-judge-recommendation.test.ts": 15334,
"test/skill-e2e-arm-benchmark.test.ts": 75588,
"test/skill-e2e-aside.test.ts": 1000,
"test/skill-e2e-auq-consistency.test.ts": 70429,
"test/skill-e2e-auq-matrix.test.ts": 165796,
"test/skill-e2e-auq-verbose-vs-carved-ab.test.ts": 58547,
"test/skill-e2e-auto-decide-preserved.test.ts": 154931,
"test/skill-e2e-autoplan-dual-voice.test.ts": 167918,
"test/skill-e2e-benchmark-providers.test.ts": 9495,
"test/skill-e2e-bws.test.ts": 1000,
"test/skill-e2e-context-skills.test.ts": 169497,
"test/skill-e2e-coverage-audit.test.ts": 1000,
"test/skill-e2e-cso.test.ts": 253498,
"test/skill-e2e-deploy.test.ts": 1000,
"test/skill-e2e-design.test.ts": 817000,
"test/skill-e2e-design.test.ts#design-consultation-core": 159257,
"test/skill-e2e-design.test.ts#design-consultation-existing": 175607,
"test/skill-e2e-design.test.ts#design-consultation-preview": 114638,
"test/skill-e2e-design.test.ts#design-consultation-research": 109573,
"test/skill-e2e-design.test.ts#design-html-slop-gate": 158970,
"test/skill-e2e-design.test.ts#plan-design-review-plan-mode": 300166,
"test/skill-e2e-diagram.test.ts": 55187,
"test/skill-e2e-first-task-scaffold.test.ts": 8563,
"test/skill-e2e-gbrain-roundtrip-local.test.ts": 1000,
"test/skill-e2e-health.test.ts": 188584,
"test/skill-e2e-hermetic-canary.test.ts": 1000,
"test/skill-e2e-ios-device.test.ts": 1000,
"test/skill-e2e-learnings.test.ts": 1000,
"test/skill-e2e-office-hours-brain-writeback.test.ts": 203044,
"test/skill-e2e-office-hours-design-draft.test.ts": 285868,
"test/skill-e2e-office-hours-phase4.test.ts": 41421,
"test/skill-e2e-office-hours-section-loading.test.ts": 1200000,
"test/skill-e2e-office-hours.test.ts": 136970,
"test/skill-e2e-outside-plan-disabled.test.ts": 53292,
"test/skill-e2e-outside-voice.test.ts": 1000,
"test/skill-e2e-overlay-harness-claude-dedicated-tools-vs-bash-sonnet.test.ts": 85282,
"test/skill-e2e-overlay-harness-claude-dedicated-tools-vs-bash.test.ts": 80465,
"test/skill-e2e-overlay-harness-opus-4-7-effort-match-trivial.test.ts": 49282,
"test/skill-e2e-overlay-harness-opus-4-7-literal-interpretation.test.ts": 318532,
"test/skill-e2e-plan-ceo-mode-routing.test.ts": 443504,
"test/skill-e2e-plan-ceo-review-section-loading.test.ts": 342250,
"test/skill-e2e-plan-ceo-split-overflow.test.ts": 504266,
"test/skill-e2e-plan-decision-classification.test.ts": 93469,
"test/skill-e2e-plan-design-finding-floor.test.ts": 155538,
"test/skill-e2e-plan-design-plan-mode.test.ts": 106608,
"test/skill-e2e-plan-devex-peer-comparison-classification.test.ts": 79786,
"test/skill-e2e-plan-eng-finding-floor.test.ts": 388666,
"test/skill-e2e-plan-eng-multi-finding-batching.test.ts": 1318488,
"test/skill-e2e-plan-eng-plan-mode.test.ts": 229226,
"test/skill-e2e-plan-format.test.ts": 219670,
"test/skill-e2e-plan-prosons.test.ts": 163659,
"test/skill-e2e-plan-tune.test.ts": 1000,
"test/skill-e2e-plan.test.ts": 824000,
"test/skill-e2e-plan.test.ts#plan-ceo-review": 136101,
"test/skill-e2e-plan.test.ts#plan-ceo-review-expansion-energy": 91984,
"test/skill-e2e-plan.test.ts#plan-ceo-review-selective": 267212,
"test/skill-e2e-plan.test.ts#plan-eng-review": 128506,
"test/skill-e2e-plan.test.ts#plan-eng-review-artifact": 164137,
"test/skill-e2e-qa-bugs.test.ts": 333847,
"test/skill-e2e-qa-workflow.test.ts": 403953,
"test/skill-e2e-retro.test.ts": 166711,
"test/skill-e2e-review-army.test.ts": 511000,
"test/skill-e2e-review-army.test.ts#review-army-consensus": 277908,
"test/skill-e2e-review-army.test.ts#review-army-red-team": 88882,
"test/skill-e2e-review-army.test.ts#review-army-simplification": 136644,
"test/skill-e2e-review-army.test.ts#review-army-simplification-precision": 23884,
"test/skill-e2e-review-attribution.test.ts": 1000,
"test/skill-e2e-review.test.ts": 179362,
"test/skill-e2e-session-intelligence.test.ts": 1000,
"test/skill-e2e-setup-gbrain-bad-token.test.ts": 42912,
"test/skill-e2e-setup-gbrain-path4-local-pglite.test.ts": 165743,
"test/skill-e2e-setup-gbrain-remote.test.ts": 121127,
"test/skill-e2e-shared-libs-periodic.test.ts": 369660,
"test/skill-e2e-ship-section-loading.test.ts": 255273,
"test/skill-e2e-skillify.test.ts": 58522,
"test/skill-e2e-sync-gbrain-readiness.test.ts": 60234,
"test/skill-e2e-third-party-actions.test.ts": 1000,
"test/skill-e2e-triage.test.ts": 1000,
"test/skill-e2e-workflow.test.ts": 1000,
"test/skill-llm-eval.test.ts": 383454,
"test/skill-routing-e2e.test.ts": 68843
}
}
}