feat(demo): add interview quality audit

mvp/eval/reports/baseline-report.json

@@ -1,14 +1,14 @@
 {
-  "totalCases" : 10,
-  "passedCases" : 10,
+  "totalCases" : 12,
+  "passedCases" : 12,
   "passRate" : 1.0,
   "verdictDistribution" : {
-    "PASS" : 4,
-    "LOW_CONFID" : 5,
+    "PASS" : 5,
+    "LOW_CONFID" : 6,
     "REJECT" : 1
   },
-  "averageToolCallCount" : 1.5,
-  "averageDurationMs" : 39800.0,
+  "averageToolCallCount" : 1.4166666666666667,
+  "averageDurationMs" : 38500.0,
   "results" : [ {
     "caseId" : "narrow-highcpu-observation",
     "title" : "Narrow HighCPU observation",
@@ -22,10 +22,31 @@
     },
     "gatekeeperStatus" : "pass",
     "gatekeeperRuleSetVersion" : "gatekeeper-rules-v1",
+    "promptAuditVersion" : null,
     "composerStatus" : "valid",
     "claimCheckCount" : 1,
+    "gatekeeperRuleCount" : 1,
     "toolCallCount" : 1,
     "durationMs" : 18000
+  }, {
+    "caseId" : "prompt-gatekeeper-audit-closure",
+    "title" : "Prompt and Gatekeeper audit closure",
+    "passed" : true,
+    "failedChecks" : [ ],
+    "verdict" : "PASS",
+    "matchedKeywordCount" : 3,
+    "requiredKeywordCount" : 3,
+    "evidenceCoverage" : {
+      "query_metrics" : true
+    },
+    "gatekeeperStatus" : "pass",
+    "gatekeeperRuleSetVersion" : "gatekeeper-rules-v1",
+    "promptAuditVersion" : "chat-prompts-v1",
+    "composerStatus" : "valid",
+    "claimCheckCount" : 1,
+    "gatekeeperRuleCount" : 2,
+    "toolCallCount" : 1,
+    "durationMs" : 19000
   }, {
     "caseId" : "hikari-no-evidence-negative-observation",
     "title" : "Hikari no-evidence negative observation",
@@ -39,8 +60,10 @@
     },
     "gatekeeperStatus" : "pass",
     "gatekeeperRuleSetVersion" : "gatekeeper-rules-v1",
+    "promptAuditVersion" : null,
     "composerStatus" : "valid",
     "claimCheckCount" : 1,
+    "gatekeeperRuleCount" : 1,
     "toolCallCount" : 1,
     "durationMs" : 21000
   }, {
@@ -58,8 +81,10 @@
     },
     "gatekeeperStatus" : null,
     "gatekeeperRuleSetVersion" : null,
+    "promptAuditVersion" : null,
     "composerStatus" : null,
     "claimCheckCount" : null,
+    "gatekeeperRuleCount" : null,
     "toolCallCount" : 3,
     "durationMs" : 42000
   }, {
@@ -76,8 +101,10 @@
     },
     "gatekeeperStatus" : null,
     "gatekeeperRuleSetVersion" : null,
+    "promptAuditVersion" : null,
     "composerStatus" : null,
     "claimCheckCount" : null,
+    "gatekeeperRuleCount" : null,
     "toolCallCount" : 2,
     "durationMs" : 51000
   }, {
@@ -93,8 +120,10 @@
     },
     "gatekeeperStatus" : null,
     "gatekeeperRuleSetVersion" : null,
+    "promptAuditVersion" : null,
     "composerStatus" : null,
     "claimCheckCount" : null,
+    "gatekeeperRuleCount" : null,
     "toolCallCount" : 1,
     "durationMs" : 36000
   }, {
@@ -111,8 +140,10 @@
     },
     "gatekeeperStatus" : null,
     "gatekeeperRuleSetVersion" : null,
+    "promptAuditVersion" : null,
     "composerStatus" : null,
     "claimCheckCount" : null,
+    "gatekeeperRuleCount" : null,
     "toolCallCount" : 2,
     "durationMs" : 47000
   }, {
@@ -129,8 +160,10 @@
     },
     "gatekeeperStatus" : null,
     "gatekeeperRuleSetVersion" : null,
+    "promptAuditVersion" : null,
     "composerStatus" : null,
     "claimCheckCount" : null,
+    "gatekeeperRuleCount" : null,
     "toolCallCount" : 2,
     "durationMs" : 53000
   }, {
@@ -146,8 +179,10 @@
     },
     "gatekeeperStatus" : "fail",
     "gatekeeperRuleSetVersion" : null,
+    "promptAuditVersion" : null,
     "composerStatus" : "valid",
     "claimCheckCount" : 1,
+    "gatekeeperRuleCount" : null,
     "toolCallCount" : 1,
     "durationMs" : 39000
   }, {
@@ -163,10 +198,31 @@
     },
     "gatekeeperStatus" : "pass",
     "gatekeeperRuleSetVersion" : null,
+    "promptAuditVersion" : null,
     "composerStatus" : "valid",
     "claimCheckCount" : 2,
+    "gatekeeperRuleCount" : null,
     "toolCallCount" : 1,
     "durationMs" : 44000
+  }, {
+    "caseId" : "audit-metadata-low-confid",
+    "title" : "Audit metadata low confidence",
+    "passed" : true,
+    "failedChecks" : [ ],
+    "verdict" : "LOW_CONFID",
+    "matchedKeywordCount" : 2,
+    "requiredKeywordCount" : 2,
+    "evidenceCoverage" : {
+      "query_logs" : true
+    },
+    "gatekeeperStatus" : "pass",
+    "gatekeeperRuleSetVersion" : "gatekeeper-rules-v1",
+    "promptAuditVersion" : "chat-prompts-v1",
+    "composerStatus" : "valid",
+    "claimCheckCount" : 2,
+    "gatekeeperRuleCount" : 2,
+    "toolCallCount" : 1,
+    "durationMs" : 45000
   }, {
     "caseId" : "composer-fallback-no-raw-json",
     "title" : "Composer fallback no raw JSON",
@@ -180,8 +236,10 @@
     },
     "gatekeeperStatus" : "pass",
     "gatekeeperRuleSetVersion" : null,
+    "promptAuditVersion" : null,
     "composerStatus" : "composer_malformed",
     "claimCheckCount" : 2,
+    "gatekeeperRuleCount" : null,
     "toolCallCount" : 1,
     "durationMs" : 47000
   } ]