test(evals): version personal confirmation semantics explicitly

Co-Authored-By: Paperclip <noreply@paperclip.ing>
This commit is contained in:
DottaandPaperclip committed 2026-11-04 09:15:25 -06:00
1 parent 2b19fc60ab
commit 07b67a517b
2 files changed
+2 -2

No files matched your search

@@ -4981,7 +4981,7 @@
"../../ui/src/pages/secrets/SetMyUserSecretDialog.tsx",
"chat-scenarios/secrets.yaml"
],
"oracleVersion": "paperclip.chat-catalog.personal-secret.v3",
"oracleVersion": "paperclip.chat-catalog.personal-secret.v4",
"expectedRunCount": 3,
"expectedHumanMessageCount": 2,
"minimumRunCount": 3,
@@ -400,7 +400,7 @@ export const personalSecretExternalCases = [
if (!o?.state.initialQuestionId || !gradePersonalSecret(value).passed) return;
return { interactionId: String(o.state.initialQuestionId), sourceRunId: String(o.state.initialRunId), userId: String(o.state.currentPersonId) };
},
oracleVersion: "paperclip.chat-catalog.personal-secret.v3",
oracleVersion: "paperclip.chat-catalog.personal-secret.v4",
setupPolicy: { readiness: "preserve-scenario", invariantCheckIds: ["current-owner-missing-required-personal-value"] },
expectedRunCount: 3,
minimumRunCount: 3,