From c50788e3d43a7dbfe3145bb51c885fed7e8a5a6d Mon Sep 17 00:00:00 2001
From: bayger <patryk.bajer@gmail.com>
Date: Thu, 18 Jun 2026 16:22:06 +0200
Subject: [PATCH 1/2] Add score and full pass stats to test run pass/fail tab

---
 src/views/testing/TestRunDetailView.vue | 31 +++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/src/views/testing/TestRunDetailView.vue b/src/views/testing/TestRunDetailView.vue
index 4283f40..a3c1421 100644
--- a/src/views/testing/TestRunDetailView.vue
+++ b/src/views/testing/TestRunDetailView.vue
@@ -278,6 +278,17 @@ const passStats = computed(() => {
   return { total, passed, pct: Math.round((passed / total) * 100) }
 })
 
+const fullPassStats = computed(() => {
+  if (checkedFields.value.length === 0 || conversations.value.length === 0) return null
+  const completed = conversations.value.filter(
+    c => c.status !== 'queued' && c.status !== 'in_progress' && c.status !== 'error'
+  )
+  const fullPass = completed.filter(
+    c => checkedFields.value.every(f => isPassing(c, f))
+  ).length
+  return { total: completed.length, fullPass }
+})
+
 // ── Status helpers ─────────────────────────────────────────────
 
 function runStatusBadgeClass(status: ScenarioRunStatus): string {
@@ -495,6 +506,9 @@ function openConversation(conv: ScenarioConversationResponse) {
               <div class="text-sm text-gray-600 dark:text-gray-400">
                 <div class="font-medium text-gray-800 dark:text-gray-200">{{ passStats.passed }} / {{ passStats.total }} checks passed</div>
                 <div>{{ conversations.length }} conversations × {{ checkedFields.length }} checked fields</div>
+                <div v-if="fullPassStats">
+                  <span class="font-medium" :class="fullPassStats.fullPass === fullPassStats.total ? 'text-green-600 dark:text-green-400' : 'text-gray-800 dark:text-gray-200'">{{ fullPassStats.fullPass }}/{{ fullPassStats.total }}</span> conversations with full pass
+                </div>
               </div>
             </div>
 
@@ -512,6 +526,7 @@ function openConversation(conv: ScenarioConversationResponse) {
                         class="table-header-cell text-center"
                         :title="'Expected: ' + JSON.stringify(field.expectedValue)"
                       >{{ field.label }}</th>
+                      <th class="table-header-cell text-center">Score</th>
                       <th class="table-header-cell text-center">Result</th>
                     </tr>
                   </thead>
@@ -546,6 +561,22 @@ function openConversation(conv: ScenarioConversationResponse) {
                           <XCircle class="w-5 h-5 text-red-500 dark:text-red-400 inline-block" />
                         </span>
                       </td>
+                      <td class="table-cell text-center">
+                        <template v-if="conv.status === 'queued' || conv.status === 'in_progress'">
+                          <Clock class="w-4 h-4 text-gray-400 inline-block" />
+                        </template>
+                        <template v-else-if="conv.status === 'error'">
+                          <MinusCircle class="w-4 h-4 text-gray-400 inline-block" />
+                        </template>
+                        <template v-else>
+                          <span
+                            :class="checkedFields.every(f => isPassing(conv, f)) ? 'text-green-600 dark:text-green-400' : checkedFields.filter(f => isPassing(conv, f)).length > 0 ? 'text-yellow-600 dark:text-yellow-400' : 'text-red-600 dark:text-red-400'"
+                            class="text-xs font-semibold"
+                          >
+                            {{ Math.round((checkedFields.filter(f => isPassing(conv, f)).length / checkedFields.length) * 100) }}%
+                          </span>
+                        </template>
+                      </td>
                       <td class="table-cell text-center">
                         <template v-if="conv.status === 'queued' || conv.status === 'in_progress'">
                           <Clock class="w-4 h-4 text-gray-400 inline-block" />

From 99ff18d224165d343ed01b9f26f2e71037c75f83 Mon Sep 17 00:00:00 2001
From: bayger <patryk.bajer@gmail.com>
Date: Thu, 18 Jun 2026 21:25:36 +0200
Subject: [PATCH 2/2] Add pass rate column to test runs list view using backend
 testStatistics

---
 src/api/generated/Api.ts               |  78 +++++++++
 src/api/generated/data-contracts.ts    |  52 ++++++
 src/api/openapi.json                   | 220 +++++++++++++++++++++++++
 src/views/testing/TestRunsListView.vue |  14 ++
 4 files changed, 364 insertions(+)

diff --git a/src/api/generated/Api.ts b/src/api/generated/Api.ts
index 135eec0..75adac6 100644
--- a/src/api/generated/Api.ts
+++ b/src/api/generated/Api.ts
@@ -13604,6 +13604,19 @@ export class Api<
          * @min 0
          */
         errorCount: number;
+        /** Detailed test statistics for this run */
+        testStatistics: {
+          /**
+           * Total number of individual test assertions that passed across all conversations
+           * @min 0
+           */
+          passedTests: number;
+          /**
+           * Total number of individual test assertions that failed across all conversations
+           * @min 0
+           */
+          failedTests: number;
+        } | null;
         /** Additional metadata */
         metadata: Record<string, any>;
         /** Version number for optimistic locking */
@@ -13697,6 +13710,19 @@ export class Api<
            * @min 0
            */
           errorCount: number;
+          /** Detailed test statistics for this run */
+          testStatistics: {
+            /**
+             * Total number of individual test assertions that passed across all conversations
+             * @min 0
+             */
+            passedTests: number;
+            /**
+             * Total number of individual test assertions that failed across all conversations
+             * @min 0
+             */
+            failedTests: number;
+          } | null;
           /** Additional metadata */
           metadata: Record<string, any>;
           /** Version number for optimistic locking */
@@ -13775,6 +13801,19 @@ export class Api<
          * @min 0
          */
         errorCount: number;
+        /** Detailed test statistics for this run */
+        testStatistics: {
+          /**
+           * Total number of individual test assertions that passed across all conversations
+           * @min 0
+           */
+          passedTests: number;
+          /**
+           * Total number of individual test assertions that failed across all conversations
+           * @min 0
+           */
+          failedTests: number;
+        } | null;
         /** Additional metadata */
         metadata: Record<string, any>;
         /** Version number for optimistic locking */
@@ -13853,6 +13892,19 @@ export class Api<
          * @min 0
          */
         errorCount: number;
+        /** Detailed test statistics for this run */
+        testStatistics: {
+          /**
+           * Total number of individual test assertions that passed across all conversations
+           * @min 0
+           */
+          passedTests: number;
+          /**
+           * Total number of individual test assertions that failed across all conversations
+           * @min 0
+           */
+          failedTests: number;
+        } | null;
         /** Additional metadata */
         metadata: Record<string, any>;
         /** Version number for optimistic locking */
@@ -14013,6 +14065,19 @@ export class Api<
           dataExtractionResults: Record<string, any>;
           /** Post-processed data transformation results */
           dataTransformationResults: Record<string, any>;
+          /** Detailed test statistics for this conversation */
+          testStatistics: {
+            /**
+             * Number of individual test assertions that passed
+             * @min 0
+             */
+            passedTests: number;
+            /**
+             * Number of individual test assertions that failed
+             * @min 0
+             */
+            failedTests: number;
+          } | null;
           /** Additional metadata */
           metadata: Record<string, any>;
           /** Version number for optimistic locking */
@@ -14104,6 +14169,19 @@ export class Api<
         dataExtractionResults: Record<string, any>;
         /** Post-processed data transformation results */
         dataTransformationResults: Record<string, any>;
+        /** Detailed test statistics for this conversation */
+        testStatistics: {
+          /**
+           * Number of individual test assertions that passed
+           * @min 0
+           */
+          passedTests: number;
+          /**
+           * Number of individual test assertions that failed
+           * @min 0
+           */
+          failedTests: number;
+        } | null;
         /** Additional metadata */
         metadata: Record<string, any>;
         /** Version number for optimistic locking */
diff --git a/src/api/generated/data-contracts.ts b/src/api/generated/data-contracts.ts
index b143137..3f01ade 100644
--- a/src/api/generated/data-contracts.ts
+++ b/src/api/generated/data-contracts.ts
@@ -9028,6 +9028,19 @@ export interface ScenarioRunResponse {
    * @min 0
    */
   errorCount: number;
+  /** Detailed test statistics for this run */
+  testStatistics: {
+    /**
+     * Total number of individual test assertions that passed across all conversations
+     * @min 0
+     */
+    passedTests: number;
+    /**
+     * Total number of individual test assertions that failed across all conversations
+     * @min 0
+     */
+    failedTests: number;
+  } | null;
   /** Additional metadata */
   metadata: Record<string, any>;
   /** Version number for optimistic locking */
@@ -9066,6 +9079,19 @@ export interface ScenarioRunListResponse {
      * @min 0
      */
     errorCount: number;
+    /** Detailed test statistics for this run */
+    testStatistics: {
+      /**
+       * Total number of individual test assertions that passed across all conversations
+       * @min 0
+       */
+      passedTests: number;
+      /**
+       * Total number of individual test assertions that failed across all conversations
+       * @min 0
+       */
+      failedTests: number;
+    } | null;
     /** Additional metadata */
     metadata: Record<string, any>;
     /** Version number for optimistic locking */
@@ -9134,6 +9160,19 @@ export interface ScenarioConversationResponse {
   dataExtractionResults: Record<string, any>;
   /** Post-processed data transformation results */
   dataTransformationResults: Record<string, any>;
+  /** Detailed test statistics for this conversation */
+  testStatistics: {
+    /**
+     * Number of individual test assertions that passed
+     * @min 0
+     */
+    passedTests: number;
+    /**
+     * Number of individual test assertions that failed
+     * @min 0
+     */
+    failedTests: number;
+  } | null;
   /** Additional metadata */
   metadata: Record<string, any>;
   /** Version number for optimistic locking */
@@ -9185,6 +9224,19 @@ export interface ScenarioConversationListResponse {
     dataExtractionResults: Record<string, any>;
     /** Post-processed data transformation results */
     dataTransformationResults: Record<string, any>;
+    /** Detailed test statistics for this conversation */
+    testStatistics: {
+      /**
+       * Number of individual test assertions that passed
+       * @min 0
+       */
+      passedTests: number;
+      /**
+       * Number of individual test assertions that failed
+       * @min 0
+       */
+      failedTests: number;
+    } | null;
     /** Additional metadata */
     metadata: Record<string, any>;
     /** Version number for optimistic locking */
diff --git a/src/api/openapi.json b/src/api/openapi.json
index 9ef98d0..f1ff79b 100644
--- a/src/api/openapi.json
+++ b/src/api/openapi.json
@@ -20509,6 +20509,27 @@
             "minimum": 0,
             "description": "Number of conversations that errored during execution (excluded from pass/fail evaluation)"
           },
+          "testStatistics": {
+            "type": "object",
+            "nullable": true,
+            "properties": {
+              "passedTests": {
+                "type": "integer",
+                "minimum": 0,
+                "description": "Total number of individual test assertions that passed across all conversations"
+              },
+              "failedTests": {
+                "type": "integer",
+                "minimum": 0,
+                "description": "Total number of individual test assertions that failed across all conversations"
+              }
+            },
+            "required": [
+              "passedTests",
+              "failedTests"
+            ],
+            "description": "Detailed test statistics for this run"
+          },
           "metadata": {
             "type": "object",
             "nullable": true,
@@ -20543,6 +20564,7 @@
           "status",
           "statusDetails",
           "errorCount",
+          "testStatistics",
           "metadata",
           "version",
           "createdAt",
@@ -20600,6 +20622,27 @@
                   "minimum": 0,
                   "description": "Number of conversations that errored during execution (excluded from pass/fail evaluation)"
                 },
+                "testStatistics": {
+                  "type": "object",
+                  "nullable": true,
+                  "properties": {
+                    "passedTests": {
+                      "type": "integer",
+                      "minimum": 0,
+                      "description": "Total number of individual test assertions that passed across all conversations"
+                    },
+                    "failedTests": {
+                      "type": "integer",
+                      "minimum": 0,
+                      "description": "Total number of individual test assertions that failed across all conversations"
+                    }
+                  },
+                  "required": [
+                    "passedTests",
+                    "failedTests"
+                  ],
+                  "description": "Detailed test statistics for this run"
+                },
                 "metadata": {
                   "type": "object",
                   "nullable": true,
@@ -20634,6 +20677,7 @@
                 "status",
                 "statusDetails",
                 "errorCount",
+                "testStatistics",
                 "metadata",
                 "version",
                 "createdAt",
@@ -20737,6 +20781,27 @@
             },
             "description": "Post-processed data transformation results"
           },
+          "testStatistics": {
+            "type": "object",
+            "nullable": true,
+            "properties": {
+              "passedTests": {
+                "type": "integer",
+                "minimum": 0,
+                "description": "Number of individual test assertions that passed"
+              },
+              "failedTests": {
+                "type": "integer",
+                "minimum": 0,
+                "description": "Number of individual test assertions that failed"
+              }
+            },
+            "required": [
+              "passedTests",
+              "failedTests"
+            ],
+            "description": "Detailed test statistics for this conversation"
+          },
           "metadata": {
             "type": "object",
             "nullable": true,
@@ -20773,6 +20838,7 @@
           "testRunStatus",
           "dataExtractionResults",
           "dataTransformationResults",
+          "testStatistics",
           "metadata",
           "version",
           "createdAt",
@@ -20853,6 +20919,27 @@
                   },
                   "description": "Post-processed data transformation results"
                 },
+                "testStatistics": {
+                  "type": "object",
+                  "nullable": true,
+                  "properties": {
+                    "passedTests": {
+                      "type": "integer",
+                      "minimum": 0,
+                      "description": "Number of individual test assertions that passed"
+                    },
+                    "failedTests": {
+                      "type": "integer",
+                      "minimum": 0,
+                      "description": "Number of individual test assertions that failed"
+                    }
+                  },
+                  "required": [
+                    "passedTests",
+                    "failedTests"
+                  ],
+                  "description": "Detailed test statistics for this conversation"
+                },
                 "metadata": {
                   "type": "object",
                   "nullable": true,
@@ -20889,6 +20976,7 @@
                 "testRunStatus",
                 "dataExtractionResults",
                 "dataTransformationResults",
+                "testStatistics",
                 "metadata",
                 "version",
                 "createdAt",
@@ -55426,6 +55514,27 @@
                       "minimum": 0,
                       "description": "Number of conversations that errored during execution (excluded from pass/fail evaluation)"
                     },
+                    "testStatistics": {
+                      "type": "object",
+                      "nullable": true,
+                      "properties": {
+                        "passedTests": {
+                          "type": "integer",
+                          "minimum": 0,
+                          "description": "Total number of individual test assertions that passed across all conversations"
+                        },
+                        "failedTests": {
+                          "type": "integer",
+                          "minimum": 0,
+                          "description": "Total number of individual test assertions that failed across all conversations"
+                        }
+                      },
+                      "required": [
+                        "passedTests",
+                        "failedTests"
+                      ],
+                      "description": "Detailed test statistics for this run"
+                    },
                     "metadata": {
                       "type": "object",
                       "nullable": true,
@@ -55460,6 +55569,7 @@
                     "status",
                     "statusDetails",
                     "errorCount",
+                    "testStatistics",
                     "metadata",
                     "version",
                     "createdAt",
@@ -55667,6 +55777,27 @@
                             "minimum": 0,
                             "description": "Number of conversations that errored during execution (excluded from pass/fail evaluation)"
                           },
+                          "testStatistics": {
+                            "type": "object",
+                            "nullable": true,
+                            "properties": {
+                              "passedTests": {
+                                "type": "integer",
+                                "minimum": 0,
+                                "description": "Total number of individual test assertions that passed across all conversations"
+                              },
+                              "failedTests": {
+                                "type": "integer",
+                                "minimum": 0,
+                                "description": "Total number of individual test assertions that failed across all conversations"
+                              }
+                            },
+                            "required": [
+                              "passedTests",
+                              "failedTests"
+                            ],
+                            "description": "Detailed test statistics for this run"
+                          },
                           "metadata": {
                             "type": "object",
                             "nullable": true,
@@ -55701,6 +55832,7 @@
                           "status",
                           "statusDetails",
                           "errorCount",
+                          "testStatistics",
                           "metadata",
                           "version",
                           "createdAt",
@@ -55822,6 +55954,27 @@
                       "minimum": 0,
                       "description": "Number of conversations that errored during execution (excluded from pass/fail evaluation)"
                     },
+                    "testStatistics": {
+                      "type": "object",
+                      "nullable": true,
+                      "properties": {
+                        "passedTests": {
+                          "type": "integer",
+                          "minimum": 0,
+                          "description": "Total number of individual test assertions that passed across all conversations"
+                        },
+                        "failedTests": {
+                          "type": "integer",
+                          "minimum": 0,
+                          "description": "Total number of individual test assertions that failed across all conversations"
+                        }
+                      },
+                      "required": [
+                        "passedTests",
+                        "failedTests"
+                      ],
+                      "description": "Detailed test statistics for this run"
+                    },
                     "metadata": {
                       "type": "object",
                       "nullable": true,
@@ -55856,6 +56009,7 @@
                     "status",
                     "statusDetails",
                     "errorCount",
+                    "testStatistics",
                     "metadata",
                     "version",
                     "createdAt",
@@ -55993,6 +56147,27 @@
                       "minimum": 0,
                       "description": "Number of conversations that errored during execution (excluded from pass/fail evaluation)"
                     },
+                    "testStatistics": {
+                      "type": "object",
+                      "nullable": true,
+                      "properties": {
+                        "passedTests": {
+                          "type": "integer",
+                          "minimum": 0,
+                          "description": "Total number of individual test assertions that passed across all conversations"
+                        },
+                        "failedTests": {
+                          "type": "integer",
+                          "minimum": 0,
+                          "description": "Total number of individual test assertions that failed across all conversations"
+                        }
+                      },
+                      "required": [
+                        "passedTests",
+                        "failedTests"
+                      ],
+                      "description": "Detailed test statistics for this run"
+                    },
                     "metadata": {
                       "type": "object",
                       "nullable": true,
@@ -56027,6 +56202,7 @@
                     "status",
                     "statusDetails",
                     "errorCount",
+                    "testStatistics",
                     "metadata",
                     "version",
                     "createdAt",
@@ -56351,6 +56527,27 @@
                             },
                             "description": "Post-processed data transformation results"
                           },
+                          "testStatistics": {
+                            "type": "object",
+                            "nullable": true,
+                            "properties": {
+                              "passedTests": {
+                                "type": "integer",
+                                "minimum": 0,
+                                "description": "Number of individual test assertions that passed"
+                              },
+                              "failedTests": {
+                                "type": "integer",
+                                "minimum": 0,
+                                "description": "Number of individual test assertions that failed"
+                              }
+                            },
+                            "required": [
+                              "passedTests",
+                              "failedTests"
+                            ],
+                            "description": "Detailed test statistics for this conversation"
+                          },
                           "metadata": {
                             "type": "object",
                             "nullable": true,
@@ -56387,6 +56584,7 @@
                           "testRunStatus",
                           "dataExtractionResults",
                           "dataTransformationResults",
+                          "testStatistics",
                           "metadata",
                           "version",
                           "createdAt",
@@ -56531,6 +56729,27 @@
                       },
                       "description": "Post-processed data transformation results"
                     },
+                    "testStatistics": {
+                      "type": "object",
+                      "nullable": true,
+                      "properties": {
+                        "passedTests": {
+                          "type": "integer",
+                          "minimum": 0,
+                          "description": "Number of individual test assertions that passed"
+                        },
+                        "failedTests": {
+                          "type": "integer",
+                          "minimum": 0,
+                          "description": "Number of individual test assertions that failed"
+                        }
+                      },
+                      "required": [
+                        "passedTests",
+                        "failedTests"
+                      ],
+                      "description": "Detailed test statistics for this conversation"
+                    },
                     "metadata": {
                       "type": "object",
                       "nullable": true,
@@ -56567,6 +56786,7 @@
                     "testRunStatus",
                     "dataExtractionResults",
                     "dataTransformationResults",
+                    "testStatistics",
                     "metadata",
                     "version",
                     "createdAt",
diff --git a/src/views/testing/TestRunsListView.vue b/src/views/testing/TestRunsListView.vue
index 608faf6..7134d17 100644
--- a/src/views/testing/TestRunsListView.vue
+++ b/src/views/testing/TestRunsListView.vue
@@ -100,6 +100,13 @@ function statusLabel(run: ScenarioRunResponse): string {
 const showRunModal = ref(false)
 const actionLoadingId = ref<string | null>(null)
 
+function passRatePct(run: ScenarioRunResponse): number {
+  if (!run.testStatistics) return 0
+  const total = run.testStatistics.passedTests + run.testStatistics.failedTests
+  if (total === 0) return 0
+  return Math.round((run.testStatistics.passedTests / total) * 100)
+}
+
 function isTerminal(run: ScenarioRunResponse): boolean {
   return run.status === ScenarioRunStatus.Passed ||
     run.status === ScenarioRunStatus.Failed ||
@@ -195,6 +202,7 @@ async function onRunStarted() {
               <th class="table-header-cell">Scenario</th>
               <th class="table-header-cell">Testers</th>
               <th class="table-header-cell">Conversations</th>
+                <th class="table-header-cell">Pass Rate</th>
               <th class="table-header-cell">Status</th>
               <th class="table-header-cell-sortable" @click="toggleSort('createdAt')">
                 <div class="flex items-center gap-1">
@@ -213,6 +221,12 @@ async function onRunStarted() {
                   {{ run.totalConversations }}
                   <AlertTriangle v-if="run.errorCount > 0" class="inline w-4 h-4 text-red-500 dark:text-red-400" :title="`${run.errorCount} conversation(s) errored`" />
                 </td>
+                <td class="table-cell">
+                  <span v-if="run.testStatistics && isTerminal(run)" :class="passRatePct(run) >= 100 ? 'text-green-600 dark:text-green-400' : passRatePct(run) > 0 ? 'text-yellow-600 dark:text-yellow-400' : 'text-red-600 dark:text-red-400'" class="font-semibold text-xs">
+                    {{ passRatePct(run) }}% ({{ run.testStatistics.passedTests }}/{{ run.testStatistics.passedTests + run.testStatistics.failedTests }})
+                  </span>
+                  <span v-else class="text-xs text-gray-400">—</span>
+                </td>
                 <td class="table-cell">
                 <span :class="statusBadgeClass(run)" :title="run.statusDetails || undefined">{{ statusLabel(run) }}</span>
               </td>