From 757e772c94447c7711938c738363283f4d548b10 Mon Sep 17 00:00:00 2001 From: Eric Bell Date: Mon, 28 Sep 2026 22:09:53 -0400 Subject: [PATCH] final staging before packaging --- .../mishandled_pro_v2/staleness.json | 130 +++++++----------- .../mishandled_pro_v2/toolkit-files.json | 2 +- 2 files changed, 50 insertions(+), 82 deletions(-) diff --git a/worker-toolkit-potion-polyglot/harbor-tasks/mishandled_pro_v2/staleness.json b/worker-toolkit-potion-polyglot/harbor-tasks/mishandled_pro_v2/staleness.json index c14469b..5d0c9c1 100644 --- a/worker-toolkit-potion-polyglot/harbor-tasks/mishandled_pro_v2/staleness.json +++ b/worker-toolkit-potion-polyglot/harbor-tasks/mishandled_pro_v2/staleness.json @@ -1,6 +1,6 @@ { "version": 1, - "generatedAt": "2026-09-28T19:08:30.093Z", + "generatedAt": "2026-09-28T22:38:24.037Z", "referenceRuns": [ { "runId": "reward-0.3000-wNYgXoP", @@ -34,132 +34,106 @@ "detectors": [ { "report": "detector-answer-obviousness.md", - "status": "stale", + "status": "fresh", "method": "checksums", - "changed": [ - "holistic rubric (tests/holistic-rubric.md)" - ], - "capturedAt": "2026-09-27T10:39:09.551Z", + "changed": [], + "capturedAt": "2026-09-28T19:23:17.368Z", "capturedBy": "stamp" }, { "report": "detector-broken-dev-env.md", - "status": "stale", + "status": "fresh", "method": "checksums", - "changed": [ - "holistic rubric (tests/holistic-rubric.md)" - ], - "capturedAt": "2026-09-27T11:40:49.062Z", + "changed": [], + "capturedAt": "2026-09-28T19:30:28.417Z", "capturedBy": "stamp" }, { "report": "detector-credential-leakage.md", - "status": "stale", + "status": "fresh", "method": "checksums", - "changed": [ - "holistic rubric (tests/holistic-rubric.md)" - ], - "capturedAt": "2026-09-27T10:46:06.445Z", + "changed": [], + "capturedAt": "2026-09-28T19:33:31.341Z", "capturedBy": "stamp" }, { "report": "detector-cross-task-reference.md", - "status": "stale", + "status": "fresh", "method": "checksums", - "changed": [ - "holistic rubric (tests/holistic-rubric.md)" - ], - "capturedAt": "2026-09-27T10:50:07.873Z", + "changed": [], + "capturedAt": "2026-09-28T19:34:49.008Z", "capturedBy": "stamp" }, { "report": "detector-dimension-misapplication.md", - "status": "stale", + "status": "fresh", "method": "checksums", - "changed": [ - "holistic rubric (tests/holistic-rubric.md)" - ], - "capturedAt": "2026-09-27T10:56:37.840Z", + "changed": [], + "capturedAt": "2026-09-28T19:42:30.726Z", "capturedBy": "stamp" }, { "report": "detector-fact-check-rubric-claims.md", - "status": "stale", + "status": "fresh", "method": "checksums", - "changed": [ - "holistic rubric (tests/holistic-rubric.md)" - ], - "capturedAt": "2026-09-27T11:12:22.622Z", + "changed": [], + "capturedAt": "2026-09-28T20:54:13.728Z", "capturedBy": "stamp" }, { "report": "detector-good-response-defined.md", - "status": "stale", + "status": "fresh", "method": "checksums", - "changed": [ - "holistic rubric (tests/holistic-rubric.md)" - ], - "capturedAt": "2026-09-27T11:14:33.977Z", + "changed": [], + "capturedAt": "2026-09-28T21:01:32.392Z", "capturedBy": "stamp" }, { "report": "detector-good-response-exhaustiveness.md", - "status": "stale", + "status": "fresh", "method": "checksums", - "changed": [ - "holistic rubric (tests/holistic-rubric.md)" - ], - "capturedAt": "2026-09-27T11:16:21.813Z", + "changed": [], + "capturedAt": "2026-09-28T20:58:29.897Z", "capturedBy": "stamp" }, { "report": "detector-meaningful-failure.md", - "status": "stale", + "status": "fresh", "method": "checksums", - "changed": [ - "holistic rubric (tests/holistic-rubric.md)" - ], - "capturedAt": "2026-09-27T10:27:37.476Z", + "changed": [], + "capturedAt": "2026-09-28T21:12:58.157Z", "capturedBy": "stamp" }, { "report": "detector-offline-verifiability.md", - "status": "stale", + "status": "fresh", "method": "checksums", - "changed": [ - "holistic rubric (tests/holistic-rubric.md)" - ], - "capturedAt": "2026-09-27T11:20:45.984Z", + "changed": [], + "capturedAt": "2026-09-28T22:22:49.326Z", "capturedBy": "stamp" }, { "report": "detector-over-hinting.md", - "status": "stale", + "status": "fresh", "method": "checksums", - "changed": [ - "holistic rubric (tests/holistic-rubric.md)" - ], - "capturedAt": "2026-09-27T11:21:54.713Z", + "changed": [], + "capturedAt": "2026-09-28T22:24:54.663Z", "capturedBy": "stamp" }, { "report": "detector-rubric-clarity.md", - "status": "stale", + "status": "fresh", "method": "checksums", - "changed": [ - "holistic rubric (tests/holistic-rubric.md)" - ], - "capturedAt": "2026-09-27T11:23:34.524Z", + "changed": [], + "capturedAt": "2026-09-28T22:26:54.495Z", "capturedBy": "stamp" }, { "report": "detector-rubric-coverage.md", - "status": "stale", + "status": "fresh", "method": "checksums", - "changed": [ - "atomic rubric (tests/atomic-rubric.yaml)" - ], - "capturedAt": "2026-09-28T18:12:01.032Z", + "changed": [], + "capturedAt": "2026-09-28T22:34:46.172Z", "capturedBy": "stamp" }, { @@ -172,32 +146,26 @@ }, { "report": "detector-rubric-generality.md", - "status": "stale", + "status": "fresh", "method": "checksums", - "changed": [ - "holistic rubric (tests/holistic-rubric.md)" - ], - "capturedAt": "2026-09-27T11:24:49.860Z", + "changed": [], + "capturedAt": "2026-09-28T22:28:12.925Z", "capturedBy": "stamp" }, { "report": "detector-run-behaviors.md", - "status": "stale", + "status": "fresh", "method": "checksums", - "changed": [ - "holistic rubric (tests/holistic-rubric.md)" - ], - "capturedAt": "2026-09-27T11:32:43.695Z", + "changed": [], + "capturedAt": "2026-09-28T22:31:42.514Z", "capturedBy": "stamp" }, { "report": "detector-snapshot-leakage.md", - "status": "stale", + "status": "fresh", "method": "checksums", - "changed": [ - "holistic rubric (tests/holistic-rubric.md)" - ], - "capturedAt": "2026-09-27T11:26:49.794Z", + "changed": [], + "capturedAt": "2026-09-28T22:33:08.497Z", "capturedBy": "stamp" } ] diff --git a/worker-toolkit-potion-polyglot/harbor-tasks/mishandled_pro_v2/toolkit-files.json b/worker-toolkit-potion-polyglot/harbor-tasks/mishandled_pro_v2/toolkit-files.json index b4577b1..16c73be 100644 --- a/worker-toolkit-potion-polyglot/harbor-tasks/mishandled_pro_v2/toolkit-files.json +++ b/worker-toolkit-potion-polyglot/harbor-tasks/mishandled_pro_v2/toolkit-files.json @@ -1,6 +1,6 @@ { "version": 1, - "generatedAt": "2026-09-28T19:08:30.147Z", + "generatedAt": "2026-09-28T22:38:24.092Z", "files": [ { "taskPath": "environment/Dockerfile",