chore(evals): declare calibrated secret acknowledgments and skill caveats

Co-Authored-By: Paperclip <[email protected]>

tests/runner-e2e/CHAT-FEATURES.md

@@ -534,3 +534,33 @@ permissions, human/native bounds and clocks remain unchanged. Cap 2 and zero
 retries remain the controller policy. Existing candidate core overlays stay
 unmerged, and the held full-catalog gate remains 196 of 244. The next native
 measurement is still required; none of these local controls regrades an original.
+
+
+The next secret-pair measurement retains launch 3310's one original PASS and three
+original FAILURES. Multipart question v6 was independently verified on the same
+form without dismissal or replacement, with exact real answers and one continuation
+in 241214ms of its original 300000ms cell. This does not prove reliability or isolate
+the fixture change as the sole cause.
+
+Company secret v17 recognizes an ordered secure-save acknowledgment across bound
+explanatory clauses, while rejecting a declined save or acknowledgment. Its original
+initial native succeeded in 344242ms; only 86070ms remained at the false pre-human
+gate. Measured handlers do not explain that latency, and no avoidable latency bug
+was proved. Human entry and later native turns remain unqualified.
+
+Personal secret v16 preserves the canonical saved confirmation policy through real
+secure entry, acceptance and independent accounting. Both supported wake policies
+must match the original saved card exactly. The actual wake-on-accept/After Saving
+card was rejected before private entry; canceled or negated acknowledgments remain
+rejected. Team install v10 accepts a bounded qualifier on the exact required-skill
+subject for truthful partial-installation reporting. Its local calibration does
+not regrade original 5242 or provide runtime-migration credit; the fifteen other
+saved-state and phase checks remain required.
+
+Only Company, Personal and Team versions change in this batch. All 244 YAML
+queries, contexts, outcomes, permissions, human/native bounds, model and clocks
+remain fixed. The next measurement is only the Company and Personal secret pair,
+with cap 2, zero automatic retries and original 480000ms/660000ms cells. Team remains
+calibrated locally; the final uniform ten is still required on this same source.
+All original grades, historical conditions, unmerged core holds and the 196/244
+full-catalog gate remain intact.

tests/runner-e2e/chat-catalog-descriptors.json

@@ -4923,7 +4923,7 @@
       "chat-flow.ts",
       "chat-scenarios/secrets.yaml"
     ],
-    "oracleVersion": "paperclip.chat-catalog.company-secret-controller-baseline.v16",
+    "oracleVersion": "paperclip.chat-catalog.company-secret-controller-baseline.v17",
     "expectedRunCount": 3,
     "minimumRunCount": 2,
     "expectedHumanMessageCount": 2,
@@ -5009,7 +5009,7 @@
       "../../ui/src/pages/secrets/SetMyUserSecretDialog.tsx",
       "chat-scenarios/secrets.yaml"
     ],
-    "oracleVersion": "paperclip.chat-catalog.personal-secret.v15",
+    "oracleVersion": "paperclip.chat-catalog.personal-secret.v16",
     "expectedRunCount": 3,
     "expectedHumanMessageCount": 2,
     "minimumRunCount": 3,
@@ -6046,7 +6046,7 @@
       "chat-flow.ts",
       "chat-scenarios/teams.yaml"
     ],
-    "oracleVersion": "paperclip.chat-catalog.team-install.v9",
+    "oracleVersion": "paperclip.chat-catalog.team-install.v10",
     "expectedRunCount": 2,
     "expectedHumanMessageCount": 2,
     "turnTimeoutMs": 120000,

tests/runner-e2e/chat-catalog-domains/external-company-secret.ts

@@ -215,7 +215,7 @@ 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.v16",expectedRunCount:3,minimumRunCount:2,expectedHumanMessageCount:2,attemptTimeoutMs:480000,
+ oracleVersion:"paperclip.chat-catalog.company-secret-controller-baseline.v17",expectedRunCount:3,minimumRunCount:2,expectedHumanMessageCount:2,attemptTimeoutMs:480000,
  sourceFiles:["../../server/src/routes/secrets.ts","../../packages/paperclip-runner/src/cli/opencode-app-server-proxy.ts","../../packages/paperclip-runner/src/cli/opencode-proxy-finish-diagnostics.ts","../../packages/paperclip-runner/src/protocol-actions/request-human-input.ts","chat-catalog-domains/external-company-secret.ts","chat-catalog-domains/external-company-secret-confirmation.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);

tests/runner-e2e/chat-catalog-domains/external-personal-secret.ts

@@ -462,7 +462,7 @@ export const personalSecretExternalCases = [
         if (!o.state.initialQuestionId) return;
         return { interactionId: String(o.state.initialQuestionId), sourceRunId: String(o.state.initialRunId), userId: String(o.state.currentPersonId) };
       },
-      oracleVersion: "paperclip.chat-catalog.personal-secret.v15",
+      oracleVersion: "paperclip.chat-catalog.personal-secret.v16",
       setupPolicy: { readiness: "preserve-scenario", invariantCheckIds: ["current-owner-missing-required-personal-value"] },
       expectedRunCount: 3,
       minimumRunCount: 3,

tests/runner-e2e/chat-catalog-domains/external-team-install.ts

@@ -346,7 +346,7 @@ export const teamInstallExternalCases = [
     gradeTeamInstall,
     {
       authentication: "human-session",
-      oracleVersion: "paperclip.chat-catalog.team-install.v9",
+      oracleVersion: "paperclip.chat-catalog.team-install.v10",
       expectedRunCount: 2,
       expectedHumanMessageCount: 2,
       attemptTimeoutMs: 480_000,