From e2e3f73ad5733700bf35d95be2d229842793bce3 Mon Sep 17 00:00:00 2001 From: Eric Bell Date: Fri, 25 Sep 2026 15:37:33 -0400 Subject: [PATCH] final two detectors --- .../detectors/detector-rubric-generality.inputs.json | 8 ++++---- .../detectors/detector-rubric-generality.md | 2 +- .../detectors/detector-snapshot-leakage.inputs.json | 8 ++++---- .../detectors/detector-snapshot-leakage.md | 2 +- 4 files changed, 10 insertions(+), 10 deletions(-) diff --git a/worker-toolkit-potion-polyglot/harbor-tasks/mishandle_pro_v2/detectors/detector-rubric-generality.inputs.json b/worker-toolkit-potion-polyglot/harbor-tasks/mishandle_pro_v2/detectors/detector-rubric-generality.inputs.json index ad35965..16bab26 100644 --- a/worker-toolkit-potion-polyglot/harbor-tasks/mishandle_pro_v2/detectors/detector-rubric-generality.inputs.json +++ b/worker-toolkit-potion-polyglot/harbor-tasks/mishandle_pro_v2/detectors/detector-rubric-generality.inputs.json @@ -1,6 +1,6 @@ { "version": 1, - "capturedAt": "2026-09-21T01:15:20.219Z", + "capturedAt": "2026-09-25T19:35:16.571Z", "capturedBy": "stamp", "inputs": { "prompt": "29e2eb28448679a65ae264372ddf7d993e5752d0f295bf5557cc5b1578265a29", @@ -9,9 +9,9 @@ "workspacePatch": null, "gitref": "fcd8a9d", "graderGuidanceConsolidated": null, - "holisticRubric": "8aa5bbad67525ebaa5761cdfa594587472e4203fadc197cbc8eae8defdac811c", - "atomicRubric": null, + "holisticRubric": "a9ae4f43cbf6fe725e14eadb0c70fab83e37fb9939c50d3899db02312dda5b53", + "atomicRubric": "eb9436f5d6981bac64a99b9d8ecf82c669d40fea5bc7e51f21f750c2acbd4c29", "rubricsYaml": null, - "graderContext": null + "graderContext": "3ffb96c2cb47d9f2d5a0611844aff25cd826c33911572d5839a8ea34c90f5051" } } diff --git a/worker-toolkit-potion-polyglot/harbor-tasks/mishandle_pro_v2/detectors/detector-rubric-generality.md b/worker-toolkit-potion-polyglot/harbor-tasks/mishandle_pro_v2/detectors/detector-rubric-generality.md index 00abbee..c1134e9 100644 --- a/worker-toolkit-potion-polyglot/harbor-tasks/mishandle_pro_v2/detectors/detector-rubric-generality.md +++ b/worker-toolkit-potion-polyglot/harbor-tasks/mishandle_pro_v2/detectors/detector-rubric-generality.md @@ -24,4 +24,4 @@ None found. `generalizes` — the rubric defines response quality through task-specific but agent-independent properties: correct dual-envelope extraction, preservation of legacy behavior, targeted implementation scope, appropriate local verification, honest reporting, and avoidance of unsupported tier architecture. A grader can apply those standards to a new response regardless of whether it resembles any previously observed behavior. -The document contains no reference-run statistics, captured-run comparisons, prescribed overall bands, criterion signal predictions, or unconditional N/A markings. It also does not name Harbor, Pier, a grading runner, or another internal framework. References to an “AI agent,” an execution transcript, and an unequipped local container describe the response or its available environment rather than making scoring depend on a particular harness. The worked strong-response quotation is an authored example of the general criterion, not a reference run used as the comparison object. +The document contains no reference-run statistics, captured-run comparisons, prescribed overall bands, criterion signal predictions, or unconditional N/A markings. It also does not name Harbor, Pier, a sandbox, a grading runner, or another internal framework. “Trial agent” is a generic role rather than a harness name, while current HEAD, AWS, and GPU references are facts about the task and its verification limits. The worked strong-response quotation is an authored example of the general criterion, not a reference run used as the comparison object. diff --git a/worker-toolkit-potion-polyglot/harbor-tasks/mishandle_pro_v2/detectors/detector-snapshot-leakage.inputs.json b/worker-toolkit-potion-polyglot/harbor-tasks/mishandle_pro_v2/detectors/detector-snapshot-leakage.inputs.json index 87c9c2d..8b7e66f 100644 --- a/worker-toolkit-potion-polyglot/harbor-tasks/mishandle_pro_v2/detectors/detector-snapshot-leakage.inputs.json +++ b/worker-toolkit-potion-polyglot/harbor-tasks/mishandle_pro_v2/detectors/detector-snapshot-leakage.inputs.json @@ -1,6 +1,6 @@ { "version": 1, - "capturedAt": "2026-09-21T01:17:07.826Z", + "capturedAt": "2026-09-25T19:37:05.105Z", "capturedBy": "stamp", "inputs": { "prompt": "29e2eb28448679a65ae264372ddf7d993e5752d0f295bf5557cc5b1578265a29", @@ -9,9 +9,9 @@ "workspacePatch": null, "gitref": "fcd8a9d", "graderGuidanceConsolidated": null, - "holisticRubric": "8aa5bbad67525ebaa5761cdfa594587472e4203fadc197cbc8eae8defdac811c", - "atomicRubric": null, + "holisticRubric": "a9ae4f43cbf6fe725e14eadb0c70fab83e37fb9939c50d3899db02312dda5b53", + "atomicRubric": "eb9436f5d6981bac64a99b9d8ecf82c669d40fea5bc7e51f21f750c2acbd4c29", "rubricsYaml": null, - "graderContext": null + "graderContext": "3ffb96c2cb47d9f2d5a0611844aff25cd826c33911572d5839a8ea34c90f5051" } } diff --git a/worker-toolkit-potion-polyglot/harbor-tasks/mishandle_pro_v2/detectors/detector-snapshot-leakage.md b/worker-toolkit-potion-polyglot/harbor-tasks/mishandle_pro_v2/detectors/detector-snapshot-leakage.md index db8116e..2d840e0 100644 --- a/worker-toolkit-potion-polyglot/harbor-tasks/mishandle_pro_v2/detectors/detector-snapshot-leakage.md +++ b/worker-toolkit-potion-polyglot/harbor-tasks/mishandle_pro_v2/detectors/detector-snapshot-leakage.md @@ -27,7 +27,7 @@ The top-level injected environment contains only the ordinary task runtime and s The no-snapshot trigger applies. This task has a substantive rubric, but it ships no `environment/session.jsonl`, so the test agent inherits no prior conversation whose contents could reveal the rubric’s expected `_doc` diagnosis or dual-envelope repair. -The rest of `environment/` was also checked before making this call. There is no `environment/session/` sidechain directory, no `environment/workspace.patch`, and no JSONL, detector, results, self-check, planning, or notes artifact under the inspected environment tree. The shipped `workspace/` is the ordinary source repository, not answer-bearing authoring residue. Accordingly, there is no snapshot surface to compare against the rubric. +The full injected environment was checked before making this call. There is no `environment/session/` sidechain directory, no `environment/workspace.patch`, and no JSONL, detector, results, self-check, planning, or notes artifact anywhere in that environment tree. The shipped `workspace/` is the ordinary source repository, not answer-bearing authoring residue. Accordingly, there is no snapshot surface to compare against the rubric. If this task is intentionally a one-shot/manual task, no change is needed and `not-applicable` is the terminal result. The detector would become runnable only if a snapshot session or another injected conversation artifact were added.