test(evals): version negative-warning admission correction

Co-Authored-By: Paperclip <noreply@paperclip.ing>
This commit is contained in:
DottaandPaperclip committed 2026-11-04 16:43:52 -06:00
1 parent f6123a5377
commit 03d0211b25
7 files changed
+12 -12

No files matched your search

@@ -2599,7 +2599,7 @@
"chat-catalog-domains/identity-support.ts",
"chat-scenarios/connection-setup.yaml"
],
"oracleVersion": "paperclip.chat-catalog.external.v2",
"oracleVersion": "paperclip.chat-catalog.external.v3",
"expectedRunCount": 1,
"turnTimeoutMs": 120000,
"attemptTimeoutMs": 420000,
@@ -4905,7 +4905,7 @@
"chat-flow.ts",
"chat-scenarios/secrets.yaml"
],
"oracleVersion": "paperclip.chat-catalog.company-secret-controller-baseline.v5",
"oracleVersion": "paperclip.chat-catalog.company-secret-controller-baseline.v6",
"expectedRunCount": 2,
"expectedHumanMessageCount": 2,
"turnTimeoutMs": 120000,
@@ -4944,7 +4944,7 @@
"../../packages/plugins/sdk/dist/index.js",
"chat-scenarios/secrets.yaml"
],
"oracleVersion": "paperclip.chat-catalog.external.v2",
"oracleVersion": "paperclip.chat-catalog.external.v3",
"expectedRunCount": 3,
"expectedHumanMessageCount": 1,
"minimumRunCount": 3,
@@ -4981,7 +4981,7 @@
"../../ui/src/pages/secrets/SetMyUserSecretDialog.tsx",
"chat-scenarios/secrets.yaml"
],
"oracleVersion": "paperclip.chat-catalog.personal-secret.v6",
"oracleVersion": "paperclip.chat-catalog.personal-secret.v7",
"expectedRunCount": 3,
"expectedHumanMessageCount": 2,
"minimumRunCount": 3,
@@ -5013,7 +5013,7 @@
"../../server/src/services/secret-proposal-notifications.ts",
"chat-scenarios/secrets.yaml"
],
"oracleVersion": "paperclip.chat-catalog.external.v2",
"oracleVersion": "paperclip.chat-catalog.external.v3",
"expectedRunCount": 4,
"expectedHumanMessageCount": 4,
"minimumRunCount": 4,
@@ -5061,7 +5061,7 @@
"../../ui/src/pages/secrets/ImportFromVaultDialog.tsx",
"chat-scenarios/secrets.yaml"
],
"oracleVersion": "paperclip.chat-catalog.external.v2",
"oracleVersion": "paperclip.chat-catalog.external.v3",
"expectedRunCount": 3,
"expectedHumanMessageCount": 2,
"minimumRunCount": 2,
@@ -89,7 +89,7 @@ export const companySecretExternalCases=[definition("secrets.configure-company-s
const o=externalObservation(value);
if(!o?.state.initialQuestionId||!gradeCompanySecret(value).passed)return;
return {interactionId:String(o.state.initialQuestionId),sourceRunId:String(o.state.initialRunId),userId:String(o.state.currentPersonId)};
},oracleVersion:"paperclip.chat-catalog.company-secret-controller-baseline.v5",expectedRunCount:2,expectedHumanMessageCount:2,attemptTimeoutMs:480000,
},oracleVersion:"paperclip.chat-catalog.company-secret-controller-baseline.v6",expectedRunCount:2,expectedHumanMessageCount:2,attemptTimeoutMs:480000,
sourceFiles:["chat-catalog-domains/external-company-secret.ts","chat-catalog-domains/external-secret-question.ts","chat-catalog-domains/external-private-browser.ts","chat-catalog-domains/external-private-browser-worker.ts","chat-catalog-domains/external-credential-language.ts","chat-catalog-domains/external-secret-scan.ts","chat-catalog-domains/external-support.ts","chat-catalog-domains/internal-support.ts","chat-catalog-domains/identity-support.ts","live-fixtures.ts","../../server/src/services/secrets.ts","run-observations.ts","chat-flow.ts","chat-scenarios/secrets.yaml"],
async act(ctx,state){
const deadline=chatCatalogOriginalPhaseDeadline(ctx),remaining=()=>remainingIdentityObservationBudget(ctx);
@@ -441,7 +441,7 @@ 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.v6",
oracleVersion: "paperclip.chat-catalog.personal-secret.v7",
setupPolicy: { readiness: "preserve-scenario", invariantCheckIds: ["current-owner-missing-required-personal-value"] },
expectedRunCount: 3,
minimumRunCount: 3,
@@ -298,7 +298,7 @@ export const secretDeliveryExternalCases = [
},
gradeSecretDelivery,
{
oracleVersion: "paperclip.chat-catalog.external.v2", authentication: "human-session",
oracleVersion: "paperclip.chat-catalog.external.v3", authentication: "human-session",
expectedRunCount: 3,
minimumRunCount: 3,
expectedHumanMessageCount: 1,
@@ -94,7 +94,7 @@ export const secretProposalExternalCases=[definition("secrets.secret-proposal",a
const worker=await identityWorker(ctx,"Morgan"),secret=await ctx.input.api.postSensitive<CompanySecret>(`${root(ctx)}/secrets`,{name:"Deployment publishing key",key:"deployment-publishing",provider:"local_encrypted",value});
try{const source=await openStandingChat(ctx),session=await ctx.input.api.get<{user:{id:string}}>("/api/auth/get-session");if(!session.user.id||session.user.id==="local-board")throw new Error("Actual authorized human review identity is required");await ctx.input.api.patch(`/api/issues/${source.id}`,{description:`The publishing credential already exists as company secret ${secret.id}, Deployment publishing key. Morgan (${worker.id}) needs the environment reference PUBLISHING_API_KEY to publish the site. No value is supplied in chat and no binding exists yet.`});return {companyId:ctx.input.fixtures.company.id,leadId:ctx.input.fixtures.agent.id,morganId:worker.id,secretId:secret.id,secretBefore:secret,sourceId:source.id,personId:session.user.id,originalQuery:ctx.scenario.query};}catch(error){await ctx.input.api.delete(`/api/secrets/${secret.id}`,{allowNotFound:true});privateValues.delete(ctx);throw error;}
},gradeSecretProposal,{
oracleVersion: "paperclip.chat-catalog.external.v2", authentication:"human-session",expectedRunCount:4,minimumRunCount:4,expectedHumanMessageCount:4,attemptTimeoutMs:840000,
oracleVersion: "paperclip.chat-catalog.external.v3", authentication:"human-session",expectedRunCount:4,minimumRunCount:4,expectedHumanMessageCount:4,attemptTimeoutMs:840000,
sourceFiles:["chat-catalog-domains/external-secret-proposal.ts","chat-catalog-domains/external-secret-scan.ts","chat-catalog-domains/external-credential-language.ts","chat-catalog-domains/identity-support.ts","chat-catalog-domains/external-support.ts","chat-catalog-domains/internal-support.ts","chat-flow.ts","run-observations.ts","../../server/src/routes/secrets.ts","../../server/src/services/secret-proposals.ts","../../server/src/services/secret-proposal-notifications.ts","chat-scenarios/secrets.yaml"],
async act(ctx,state){
const initial=await settled(ctx,1),pending=(await proposals(ctx)).filter(row=>row.status==="pending");if(pending.length!==1||!requested(pending[0]!,state,ctx.issue()!.id)||pending[0]!.originRunId!==initial[0]!.id)throw new Error("Actual model must request exactly the intended reference binding before human review");
@@ -47,7 +47,7 @@ export const secureKeyExternalCases = [definition("connection-setup.secure-api-k
return { serverUrl: provider.url, personId: factualContextAttachment.createdByUserId, factualContextAttachment, setupPath: `/${ctx.input.fixtures.company.issuePrefix}/apps/byo` };
} catch (error) { fixtures.delete(ctx); await provider.close(); throw error; }
}, gradeSecureKey, {
oracleVersion: "paperclip.chat-catalog.external.v2", authentication: "human-session",
oracleVersion: "paperclip.chat-catalog.external.v3", authentication: "human-session",
queryAttachments: [{ stateKey: "factualContextAttachment", filename: "provider-account.md" }],
attemptTimeoutMs: 420_000,
sourceFiles: ["chat-catalog-domains/external-secure-key.ts", "chat-query-attachments.ts", "../../ui/src/App.tsx", "../../ui/src/pages/apps/app-connect-policy.ts", "../../ui/src/features/connections/ConnectionSetupFlow.tsx", "chat-catalog-domains/external-private-browser.ts", "chat-catalog-domains/external-private-browser-worker.ts", "chat-catalog-domains/external-credential-language.ts", "chat-catalog-domains/external-provider.ts", "chat-catalog-domains/external-secret-scan.ts", "run-observations.ts", "chat-catalog-domains/external-support.ts", "chat-catalog-domains/internal-support.ts", "chat-catalog-domains/identity-support.ts", "chat-scenarios/connection-setup.yaml"],
@@ -426,7 +426,7 @@ export const vaultReferenceExternalCases = [
},
gradeVaultReference,
{
oracleVersion: "paperclip.chat-catalog.external.v2", authentication: "human-session",
oracleVersion: "paperclip.chat-catalog.external.v3", authentication: "human-session",
expectedRunCount: 3,
minimumRunCount: 2,
expectedHumanMessageCount: 2,