@validate.qa/runner 1.0.64 → 1.0.65

package/dist/cli.js

@@ -3485,6 +3485,135 @@ var init_audit_pricing = __esm({
   }
 });
 
+// ../shared/dist/audit-grouping.js
+var GROUPABLE_CALL_TYPES, GROUP_LABELS, FLOW_PHASE_TYPES, FLOW_SERVER_TYPES, FLOW_PHASE_LABELS;
+var init_audit_grouping = __esm({
+  "../shared/dist/audit-grouping.js"() {
+    "use strict";
+    GROUPABLE_CALL_TYPES = /* @__PURE__ */ new Set([
+      "healIteration",
+      "healOrchestrator",
+      "generateRegressionSuite",
+      "discoveryExplore",
+      "surveyExplore",
+      "featureExplore",
+      "discoveryGenerate",
+      "discoveryPlan",
+      "discoveryGenerateSkeleton",
+      "discoveryGenerateElementContext",
+      "liveGenerate",
+      "scenarioGenerate",
+      "liveSuiteHeal",
+      "captureIteration",
+      "healAPITest",
+      "generateAPITests",
+      // Auth-prologue login-capture run (runLoginCaptureRun) — per-turn rows share a
+      // groupId so they collapse into one "Login Capture" phase card on /audit.
+      "authCapture",
+      // Assistant chat — rounds of one conversation collapse into one card.
+      "assistantChat"
+    ]);
+    GROUP_LABELS = {
+      healIteration: "healSession",
+      healOrchestrator: "healSession",
+      healAPITest: "apiHealSession",
+      generateRegressionSuite: "regressionSession",
+      generateAPITests: "apiTestGenSession",
+      discoveryExplore: "discoveryExploreSession",
+      surveyExplore: "surveyExploreSession",
+      featureExplore: "featureExploreSession",
+      discoveryGenerate: "discoveryGenerateSession",
+      discoveryGenerateSkeleton: "discoveryGenerateSession",
+      discoveryGenerateElementContext: "discoveryGenerateSession",
+      liveGenerate: "liveGenerateSession",
+      scenarioGenerate: "scenarioGenerateSession",
+      discoveryPlan: "discoveryPlanSession",
+      liveSuiteHeal: "liveSuiteHealSession",
+      captureIteration: "captureIterationSession",
+      authCapture: "authCaptureSession",
+      assistantChat: "assistantChatSession"
+    };
+    FLOW_PHASE_TYPES = /* @__PURE__ */ new Set([
+      "surveyExploreSession",
+      "featureExploreSession",
+      "discoveryAIPlanner",
+      "discoveryPlanSession",
+      "scenarioGenerateSession",
+      "liveGenerateSession",
+      "discoveryGenerateSession",
+      // Raw callTypes (for ungrouped single-turn entries like planner)
+      "surveyExplore",
+      "featureExplore",
+      "discoveryPlan",
+      "scenarioGenerate",
+      "liveGenerate",
+      "discoveryGenerate",
+      // Planner repair / retry / strengthen-gate — the one-shot extra planner call
+      // shares the base planner's discoveryFlowId, so it nests as its own phase
+      // instead of dangling as a raw camelCase row.
+      "discoveryAIPlannerRepair",
+      "discoveryAIPlannerRetry",
+      "discoveryAIPlannerStrengthenGate",
+      // Deep-run feature analyst insight (one call per feature discovery).
+      "featureInsight",
+      // Discovery v2 Call-1-authoring pivot — per-test Call 2 spawns. Each session
+      // has its OWN sessionId but shares the parent discoveryFlowId, so grouping by
+      // flowId pulls them under the same Discovery Flow card. `Cleanup` is the
+      // teardown sibling of Fix/Author and nests the same way.
+      "discoveryCall2Fix",
+      "discoveryCall2Author",
+      "discoveryCall2Cleanup",
+      // Auth-prologue login-capture run — grouped label + raw callType.
+      "authCaptureSession",
+      "authCapture"
+    ]);
+    FLOW_SERVER_TYPES = /* @__PURE__ */ new Set([
+      "healthAnalysis",
+      "apiSecurityAudit",
+      "apiSecurityAuditVerify",
+      "generateAPITests",
+      "apiTestGenSession",
+      "healAPITest",
+      "apiHealSession",
+      "healSession",
+      "healIteration"
+    ]);
+    FLOW_PHASE_LABELS = {
+      surveyExploreSession: "Survey Explore",
+      featureExploreSession: "Feature Explore",
+      discoveryAIPlanner: "Feature Analyst",
+      discoveryAIPlannerRepair: "Planner Repair",
+      discoveryAIPlannerRetry: "Planner Retry",
+      discoveryAIPlannerStrengthenGate: "Planner Strengthen Gate",
+      discoveryPlanSession: "Survey Planner",
+      scenarioGenerateSession: "Scenario Gen",
+      liveGenerateSession: "Live Browser Gen",
+      discoveryGenerateSession: "Test Generation",
+      surveyExplore: "Survey Explore",
+      featureExplore: "Feature Explore",
+      discoveryPlan: "Planner",
+      scenarioGenerate: "Scenario Gen",
+      liveGenerate: "Live Browser Gen",
+      discoveryGenerate: "Test Generation",
+      discoveryCall2Fix: "Call 2 Fix",
+      discoveryCall2Author: "Call 2 Author",
+      discoveryCall2Cleanup: "Call 2 Cleanup",
+      featureInsight: "Feature Insight",
+      healthAnalysis: "Health Analysis",
+      apiSecurityAudit: "Security Audit",
+      apiSecurityAuditVerify: "Security Verify",
+      generateAPITests: "API Test Gen",
+      apiTestGenSession: "API Test Gen",
+      healAPITest: "API Test Heal",
+      apiHealSession: "API Test Heal",
+      healSession: "Heal Session",
+      healIteration: "Heal",
+      authCapture: "Login Capture",
+      authCaptureSession: "Login Capture"
+    };
+  }
+});
+
 // ../shared/dist/discovery-har-decision.js
 function decideHarPosted(response) {
   if (!response)
@@ -5850,6 +5979,11 @@ __export(dist_exports, {
   DEFAULT_UI_VARIANT: () => DEFAULT_UI_VARIANT,
   EMAIL_FROM_IDENTITIES: () => EMAIL_FROM_IDENTITIES,
   ENVIRONMENTAL_ERROR_PREFIXES: () => ENVIRONMENTAL_ERROR_PREFIXES,
+  FLOW_PHASE_LABELS: () => FLOW_PHASE_LABELS,
+  FLOW_PHASE_TYPES: () => FLOW_PHASE_TYPES,
+  FLOW_SERVER_TYPES: () => FLOW_SERVER_TYPES,
+  GROUPABLE_CALL_TYPES: () => GROUPABLE_CALL_TYPES,
+  GROUP_LABELS: () => GROUP_LABELS,
   LEGACY_TTS_VOICE_ID_MAP: () => LEGACY_TTS_VOICE_ID_MAP,
   MAX_CREDIT_TOPUP_CENTS: () => MAX_CREDIT_TOPUP_CENTS,
   MAX_DEEPLINK_LENGTH: () => MAX_DEEPLINK_LENGTH,
@@ -6033,6 +6167,7 @@ var init_dist = __esm({
     init_mobile_deeplink();
     init_plans();
     init_audit_pricing();
+    init_audit_grouping();
     init_discovery_har_decision();
     init_assertion_classifier();
     init_assertion_strength();
@@ -350920,7 +351055,7 @@ var require_package4 = __commonJS({
   "package.json"(exports2, module2) {
     module2.exports = {
       name: "@validate.qa/runner",
-      version: "1.0.64",
+      version: "1.0.65",
       description: "validate local test runner - execute Playwright tests on your machine, connected to validate.qa cloud.",
       bin: {
         "validate-runner": "dist/cli.js"
@@ -359516,13 +359651,14 @@ ${finalVerifyResult.logs ?? ""}`;
             }
           }
         }
+        const auditStatus = info.exitReason === "abort" || info.exitReason === "timeout" ? "ERROR" : "SUCCESS";
         pushAudit({
           projectId: ctx.projectId,
           sessionId: ctx.sessionId,
           callType: info.callType,
           model: info.model,
           provider: info.provider,
-          status: "SUCCESS",
+          status: auditStatus,
           durationMs: info.durationMs,
           promptTokens: info.promptTokens,
           completionTokens: info.completionTokens,
@@ -359539,6 +359675,11 @@ ${finalVerifyResult.logs ?? ""}`;
             discoveryFlowId: run2.runId,
             ...info.callType === "authCapture" ? { featureName: "Login" } : ctx.featureName ? { featureName: ctx.featureName } : {},
             ...ctx.mode ? { discoveryMode: ctx.mode } : {},
+            // Per-session identity for Call-2 rows (parity with execute-run.ts) so
+            // Fix/Author/Cleanup phases are distinguishable in the flow card.
+            ...info.scenarioName ? { scenarioName: info.scenarioName } : {},
+            ...info.sessionKind ? { sessionKind: info.sessionKind } : {},
+            ...info.exitReason ? { exitReason: info.exitReason } : {},
             ...cliCostUsd !== void 0 ? { cliCostUsd } : {},
             ...ledgerAudit ? {
               ledger: ledgerAudit.entries,

package/dist/cli.mjs

@@ -3490,6 +3490,135 @@ var init_audit_pricing = __esm({
   }
 });
 
+// ../shared/dist/audit-grouping.js
+var GROUPABLE_CALL_TYPES, GROUP_LABELS, FLOW_PHASE_TYPES, FLOW_SERVER_TYPES, FLOW_PHASE_LABELS;
+var init_audit_grouping = __esm({
+  "../shared/dist/audit-grouping.js"() {
+    "use strict";
+    GROUPABLE_CALL_TYPES = /* @__PURE__ */ new Set([
+      "healIteration",
+      "healOrchestrator",
+      "generateRegressionSuite",
+      "discoveryExplore",
+      "surveyExplore",
+      "featureExplore",
+      "discoveryGenerate",
+      "discoveryPlan",
+      "discoveryGenerateSkeleton",
+      "discoveryGenerateElementContext",
+      "liveGenerate",
+      "scenarioGenerate",
+      "liveSuiteHeal",
+      "captureIteration",
+      "healAPITest",
+      "generateAPITests",
+      // Auth-prologue login-capture run (runLoginCaptureRun) — per-turn rows share a
+      // groupId so they collapse into one "Login Capture" phase card on /audit.
+      "authCapture",
+      // Assistant chat — rounds of one conversation collapse into one card.
+      "assistantChat"
+    ]);
+    GROUP_LABELS = {
+      healIteration: "healSession",
+      healOrchestrator: "healSession",
+      healAPITest: "apiHealSession",
+      generateRegressionSuite: "regressionSession",
+      generateAPITests: "apiTestGenSession",
+      discoveryExplore: "discoveryExploreSession",
+      surveyExplore: "surveyExploreSession",
+      featureExplore: "featureExploreSession",
+      discoveryGenerate: "discoveryGenerateSession",
+      discoveryGenerateSkeleton: "discoveryGenerateSession",
+      discoveryGenerateElementContext: "discoveryGenerateSession",
+      liveGenerate: "liveGenerateSession",
+      scenarioGenerate: "scenarioGenerateSession",
+      discoveryPlan: "discoveryPlanSession",
+      liveSuiteHeal: "liveSuiteHealSession",
+      captureIteration: "captureIterationSession",
+      authCapture: "authCaptureSession",
+      assistantChat: "assistantChatSession"
+    };
+    FLOW_PHASE_TYPES = /* @__PURE__ */ new Set([
+      "surveyExploreSession",
+      "featureExploreSession",
+      "discoveryAIPlanner",
+      "discoveryPlanSession",
+      "scenarioGenerateSession",
+      "liveGenerateSession",
+      "discoveryGenerateSession",
+      // Raw callTypes (for ungrouped single-turn entries like planner)
+      "surveyExplore",
+      "featureExplore",
+      "discoveryPlan",
+      "scenarioGenerate",
+      "liveGenerate",
+      "discoveryGenerate",
+      // Planner repair / retry / strengthen-gate — the one-shot extra planner call
+      // shares the base planner's discoveryFlowId, so it nests as its own phase
+      // instead of dangling as a raw camelCase row.
+      "discoveryAIPlannerRepair",
+      "discoveryAIPlannerRetry",
+      "discoveryAIPlannerStrengthenGate",
+      // Deep-run feature analyst insight (one call per feature discovery).
+      "featureInsight",
+      // Discovery v2 Call-1-authoring pivot — per-test Call 2 spawns. Each session
+      // has its OWN sessionId but shares the parent discoveryFlowId, so grouping by
+      // flowId pulls them under the same Discovery Flow card. `Cleanup` is the
+      // teardown sibling of Fix/Author and nests the same way.
+      "discoveryCall2Fix",
+      "discoveryCall2Author",
+      "discoveryCall2Cleanup",
+      // Auth-prologue login-capture run — grouped label + raw callType.
+      "authCaptureSession",
+      "authCapture"
+    ]);
+    FLOW_SERVER_TYPES = /* @__PURE__ */ new Set([
+      "healthAnalysis",
+      "apiSecurityAudit",
+      "apiSecurityAuditVerify",
+      "generateAPITests",
+      "apiTestGenSession",
+      "healAPITest",
+      "apiHealSession",
+      "healSession",
+      "healIteration"
+    ]);
+    FLOW_PHASE_LABELS = {
+      surveyExploreSession: "Survey Explore",
+      featureExploreSession: "Feature Explore",
+      discoveryAIPlanner: "Feature Analyst",
+      discoveryAIPlannerRepair: "Planner Repair",
+      discoveryAIPlannerRetry: "Planner Retry",
+      discoveryAIPlannerStrengthenGate: "Planner Strengthen Gate",
+      discoveryPlanSession: "Survey Planner",
+      scenarioGenerateSession: "Scenario Gen",
+      liveGenerateSession: "Live Browser Gen",
+      discoveryGenerateSession: "Test Generation",
+      surveyExplore: "Survey Explore",
+      featureExplore: "Feature Explore",
+      discoveryPlan: "Planner",
+      scenarioGenerate: "Scenario Gen",
+      liveGenerate: "Live Browser Gen",
+      discoveryGenerate: "Test Generation",
+      discoveryCall2Fix: "Call 2 Fix",
+      discoveryCall2Author: "Call 2 Author",
+      discoveryCall2Cleanup: "Call 2 Cleanup",
+      featureInsight: "Feature Insight",
+      healthAnalysis: "Health Analysis",
+      apiSecurityAudit: "Security Audit",
+      apiSecurityAuditVerify: "Security Verify",
+      generateAPITests: "API Test Gen",
+      apiTestGenSession: "API Test Gen",
+      healAPITest: "API Test Heal",
+      apiHealSession: "API Test Heal",
+      healSession: "Heal Session",
+      healIteration: "Heal",
+      authCapture: "Login Capture",
+      authCaptureSession: "Login Capture"
+    };
+  }
+});
+
 // ../shared/dist/discovery-har-decision.js
 function decideHarPosted(response) {
   if (!response)
@@ -5855,6 +5984,11 @@ __export(dist_exports, {
   DEFAULT_UI_VARIANT: () => DEFAULT_UI_VARIANT,
   EMAIL_FROM_IDENTITIES: () => EMAIL_FROM_IDENTITIES,
   ENVIRONMENTAL_ERROR_PREFIXES: () => ENVIRONMENTAL_ERROR_PREFIXES,
+  FLOW_PHASE_LABELS: () => FLOW_PHASE_LABELS,
+  FLOW_PHASE_TYPES: () => FLOW_PHASE_TYPES,
+  FLOW_SERVER_TYPES: () => FLOW_SERVER_TYPES,
+  GROUPABLE_CALL_TYPES: () => GROUPABLE_CALL_TYPES,
+  GROUP_LABELS: () => GROUP_LABELS,
   LEGACY_TTS_VOICE_ID_MAP: () => LEGACY_TTS_VOICE_ID_MAP,
   MAX_CREDIT_TOPUP_CENTS: () => MAX_CREDIT_TOPUP_CENTS,
   MAX_DEEPLINK_LENGTH: () => MAX_DEEPLINK_LENGTH,
@@ -6038,6 +6172,7 @@ var init_dist = __esm({
     init_mobile_deeplink();
     init_plans();
     init_audit_pricing();
+    init_audit_grouping();
     init_discovery_har_decision();
     init_assertion_classifier();
     init_assertion_strength();
@@ -350925,7 +351060,7 @@ var require_package4 = __commonJS({
   "package.json"(exports, module) {
     module.exports = {
       name: "@validate.qa/runner",
-      version: "1.0.64",
+      version: "1.0.65",
       description: "validate local test runner - execute Playwright tests on your machine, connected to validate.qa cloud.",
       bin: {
         "validate-runner": "dist/cli.js"
@@ -359524,13 +359659,14 @@ ${finalVerifyResult.logs ?? ""}`;
             }
           }
         }
+        const auditStatus = info.exitReason === "abort" || info.exitReason === "timeout" ? "ERROR" : "SUCCESS";
         pushAudit({
           projectId: ctx.projectId,
           sessionId: ctx.sessionId,
           callType: info.callType,
           model: info.model,
           provider: info.provider,
-          status: "SUCCESS",
+          status: auditStatus,
           durationMs: info.durationMs,
           promptTokens: info.promptTokens,
           completionTokens: info.completionTokens,
@@ -359547,6 +359683,11 @@ ${finalVerifyResult.logs ?? ""}`;
             discoveryFlowId: run2.runId,
             ...info.callType === "authCapture" ? { featureName: "Login" } : ctx.featureName ? { featureName: ctx.featureName } : {},
             ...ctx.mode ? { discoveryMode: ctx.mode } : {},
+            // Per-session identity for Call-2 rows (parity with execute-run.ts) so
+            // Fix/Author/Cleanup phases are distinguishable in the flow card.
+            ...info.scenarioName ? { scenarioName: info.scenarioName } : {},
+            ...info.sessionKind ? { sessionKind: info.sessionKind } : {},
+            ...info.exitReason ? { exitReason: info.exitReason } : {},
             ...cliCostUsd !== void 0 ? { cliCostUsd } : {},
             ...ledgerAudit ? {
               ledger: ledgerAudit.entries,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@validate.qa/runner",
-  "version": "1.0.64",
+  "version": "1.0.65",
   "description": "validate local test runner - execute Playwright tests on your machine, connected to validate.qa cloud.",
   "bin": {
     "validate-runner": "dist/cli.js"