feat(eval): add evidence pipeline acceptance closure

mvp/eval/reports/baseline-report.json

@@ -1,15 +1,49 @@
 {
-  "totalCases" : 8,
-  "passedCases" : 8,
+  "totalCases" : 10,
+  "passedCases" : 10,
   "passRate" : 1.0,
   "verdictDistribution" : {
-    "PASS" : 2,
+    "PASS" : 4,
     "LOW_CONFID" : 5,
     "REJECT" : 1
   },
-  "averageToolCallCount" : 1.625,
-  "averageDurationMs" : 44875.0,
+  "averageToolCallCount" : 1.5,
+  "averageDurationMs" : 39800.0,
   "results" : [ {
+    "caseId" : "narrow-highcpu-observation",
+    "title" : "Narrow HighCPU observation",
+    "passed" : true,
+    "failedChecks" : [ ],
+    "verdict" : "PASS",
+    "matchedKeywordCount" : 3,
+    "requiredKeywordCount" : 3,
+    "evidenceCoverage" : {
+      "query_metrics" : true
+    },
+    "gatekeeperStatus" : "pass",
+    "gatekeeperRuleSetVersion" : "gatekeeper-rules-v1",
+    "composerStatus" : "valid",
+    "claimCheckCount" : 1,
+    "toolCallCount" : 1,
+    "durationMs" : 18000
+  }, {
+    "caseId" : "hikari-no-evidence-negative-observation",
+    "title" : "Hikari no-evidence negative observation",
+    "passed" : true,
+    "failedChecks" : [ ],
+    "verdict" : "PASS",
+    "matchedKeywordCount" : 3,
+    "requiredKeywordCount" : 3,
+    "evidenceCoverage" : {
+      "query_logs" : true
+    },
+    "gatekeeperStatus" : "pass",
+    "gatekeeperRuleSetVersion" : "gatekeeper-rules-v1",
+    "composerStatus" : "valid",
+    "claimCheckCount" : 1,
+    "toolCallCount" : 1,
+    "durationMs" : 21000
+  }, {
     "caseId" : "payment-timeout",
     "title" : "Payment API timeout",
     "passed" : true,
@@ -23,6 +57,7 @@
       "query_metrics" : true
     },
     "gatekeeperStatus" : null,
+    "gatekeeperRuleSetVersion" : null,
     "composerStatus" : null,
     "claimCheckCount" : null,
     "toolCallCount" : 3,
@@ -40,6 +75,7 @@
       "query_logs" : true
     },
     "gatekeeperStatus" : null,
+    "gatekeeperRuleSetVersion" : null,
     "composerStatus" : null,
     "claimCheckCount" : null,
     "toolCallCount" : 2,
@@ -56,6 +92,7 @@
       "query_logs" : true
     },
     "gatekeeperStatus" : null,
+    "gatekeeperRuleSetVersion" : null,
     "composerStatus" : null,
     "claimCheckCount" : null,
     "toolCallCount" : 1,
@@ -73,6 +110,7 @@
       "query_logs" : true
     },
     "gatekeeperStatus" : null,
+    "gatekeeperRuleSetVersion" : null,
     "composerStatus" : null,
     "claimCheckCount" : null,
     "toolCallCount" : 2,
@@ -90,6 +128,7 @@
       "query_logs" : true
     },
     "gatekeeperStatus" : null,
+    "gatekeeperRuleSetVersion" : null,
     "composerStatus" : null,
     "claimCheckCount" : null,
     "toolCallCount" : 2,
@@ -106,6 +145,7 @@
       "query_logs" : true
     },
     "gatekeeperStatus" : "fail",
+    "gatekeeperRuleSetVersion" : null,
     "composerStatus" : "valid",
     "claimCheckCount" : 1,
     "toolCallCount" : 1,
@@ -122,6 +162,7 @@
       "query_logs" : true
     },
     "gatekeeperStatus" : "pass",
+    "gatekeeperRuleSetVersion" : null,
     "composerStatus" : "valid",
     "claimCheckCount" : 2,
     "toolCallCount" : 1,
@@ -138,9 +179,10 @@
       "query_metrics" : true
     },
     "gatekeeperStatus" : "pass",
+    "gatekeeperRuleSetVersion" : null,
     "composerStatus" : "composer_malformed",
     "claimCheckCount" : 2,
     "toolCallCount" : 1,
     "durationMs" : 47000
   } ]
-}
+}