test(evals): declare API discovery ranking provenance

Co-Authored-By: Paperclip <paperclip@paperclip.ing>
This commit is contained in:
DottaandPaperclip committed 2026-11-05 19:42:50 -06:00
1 parent e0cce66b7b
commit 2c99c248e8
3 files changed
+5 -3

No files matched your search

@@ -256,7 +256,8 @@
"chat-catalog-domains/internal-routine-audit.ts",
"../e2e/fetch-allowed-port.ts",
"../../server/src/services/native-runtime/status-decision-committer.ts",
"../../server/src/services/work-timeline.ts"
"../../server/src/services/work-timeline.ts",
"../../server/src/services/native-runtime/runner-api-catalog.ts"
],
"oracleVersion": "paperclip.chat-catalog.work-timeline.v11",
"coverageGaps": [],
@@ -4906,6 +4907,7 @@
"chat-catalog-domains/identity-support.ts",
"live-fixtures.ts",
"../../server/src/services/secrets.ts",
"../../server/src/services/native-runtime/runner-api-catalog.ts",
"../../server/src/routes/issues.ts",
"run-observations.ts",
"chat-flow.ts",
@@ -203,7 +203,7 @@ export const companySecretExternalCases=[definition("secrets.configure-company-s
optionalCompanySecretBindingApproval:true,
expectedCompanySecretBindingApproval(value){if(!gradeCompanySecret(value).passed)return;return companySecretApprovalProof(value);},
oracleVersion:"paperclip.chat-catalog.company-secret-controller-baseline.v13",expectedRunCount:3,minimumRunCount:2,expectedHumanMessageCount:2,attemptTimeoutMs:480000,
sourceFiles:["chat-catalog-domains/external-company-secret.ts","chat-catalog-domains/external-secret-proposal.ts","chat-catalog-domains/external-secret-question.ts","chat-catalog-domains/external-secret-route.ts","chat-catalog-domains/external-company-secret-menu.ts","chat-catalog-contract.ts","chat-catalog-flow.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","../../server/src/routes/issues.ts","run-observations.ts","chat-flow.ts","chat-scenarios/secrets.yaml"],
sourceFiles:["chat-catalog-domains/external-company-secret.ts","chat-catalog-domains/external-secret-proposal.ts","chat-catalog-domains/external-secret-question.ts","chat-catalog-domains/external-secret-route.ts","chat-catalog-domains/external-company-secret-menu.ts","chat-catalog-contract.ts","chat-catalog-flow.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","../../server/src/services/native-runtime/runner-api-catalog.ts","../../server/src/routes/issues.ts","run-observations.ts","chat-flow.ts","chat-scenarios/secrets.yaml"],
async act(ctx,state){
const deadline=chatCatalogOriginalPhaseDeadline(ctx),remaining=()=>remainingIdentityObservationBudget(ctx);
await waitForReply(ctx,deadline);remaining();
@@ -93,7 +93,7 @@ function timeline(): ChatCatalogCase {
await ctx.input.evidence("chat-catalog-real-launch-timeline.json", { ...state, verification: verifier.receipts, events }); return state;
}, gradeWorkTimeline);
return { ...base, oracleVersion: "paperclip.chat-catalog.work-timeline.v11", authentication: "human-session", expectedRunCount: 3, minimumRunCount: 3, attemptTimeoutMs: 720000,
sourceFiles: [...base.sourceFiles, "chat-catalog-domains/internal-work-timeline.ts", "chat-catalog-domains/internal-timeline-narrative.ts", "chat-catalog-domains/internal-timeline-verifier.ts", "chat-catalog-domains/internal-privacy.ts", "chat-catalog-domains/identity-auth.ts", "chat-catalog-domains/internal-routine-audit.ts", "../e2e/fetch-allowed-port.ts", "../../server/src/services/native-runtime/status-decision-committer.ts", "../../server/src/services/work-timeline.ts"],
sourceFiles: [...base.sourceFiles, "chat-catalog-domains/internal-work-timeline.ts", "chat-catalog-domains/internal-timeline-narrative.ts", "chat-catalog-domains/internal-timeline-verifier.ts", "chat-catalog-domains/internal-privacy.ts", "chat-catalog-domains/identity-auth.ts", "chat-catalog-domains/internal-routine-audit.ts", "../e2e/fetch-allowed-port.ts", "../../server/src/services/native-runtime/status-decision-committer.ts", "../../server/src/services/work-timeline.ts","../../server/src/services/native-runtime/runner-api-catalog.ts"],
async observe(ctx, state): Promise<Timeline> { return { ...await observeInternal(ctx, state), verification: structuredClone(verifier?.receipts ?? []), timelineEvents: await ctx.input.api.get(`/api/issues/${entity(state, "task").id}/activity`), hiddenStatus: await agentStatus(ctx, ctx.input.fixtures.agent.id, `/api/issues/${entity(state, "hiddenTask").id}`) }; },
async verifyResult(ctx, state, value) { await base.verifyResult(ctx, state, value); const source = ctx.input.page.url(); try { await ctx.input.page.goto(new URL(`/${ctx.input.fixtures.company.issuePrefix}/issues/${entity(state, "prepTask").identifier}`, ctx.input.api.baseURL).href); await expect(ctx.input.page.getByRole("heading", { name: entity(state, "prepTask").title!, exact: true })).toBeVisible(); } finally { await ctx.input.page.goto(source); await expect(ctx.input.page.getByTestId("task-chat-composer-input")).toBeVisible(); } },
async cleanup(ctx) { try { await verifier?.close(); } finally { verifier = undefined; await cleanupPrivacyProbes(ctx); await owner?.dispose(); owner = undefined; } },