@supatest/cli 0.0.28 → 0.0.30

package/README.md

@@ -15,9 +15,11 @@ Supatest AI is an AI-powered CLI that helps you write and maintain E2E tests. Us
 ## Requirements
 
 - **Node.js 18+** - [Download Node.js](https://nodejs.org/)
-- **Supatest API Key** - [Get your key](https://supatest.ai)
+- **Supatest Account** - [Sign up at supatest.ai](https://supatest.ai)
 
-## Installation
+## Getting Started
+
+### 1. Install
 
 ```bash
 npm install -g @supatest/cli
@@ -29,19 +31,43 @@ Or use npx without installing:
 npx @supatest/cli
 ```
 
-## Usage
-
-### Interactive Mode
+### 2. Login
 
-Run without arguments to start interactive mode:
+Start the CLI and authenticate:
 
 ```bash
 supatest
 ```
 
-On first run, type `/login` to authenticate with your Supatest account.
+```
+> /login
+```
+
+This opens your browser to authenticate with your Supatest account.
+
+### 3. Setup
+
+Check that your environment has the required tools:
+
+```
+> /setup
+```
+
+This verifies prerequisites like browsers and test frameworks are properly configured.
+
+### 4. Discover
+
+Scan your project to detect existing test files and configuration:
+
+```
+> /discover
+```
+
+This helps Supatest understand your test structure so it can work with your existing setup.
+
+### 5. Start Testing
 
-Then describe what you want to test:
+Now describe what you want to test:
 
 ```
 > Write a test for the login flow
@@ -113,7 +139,7 @@ test:
 ## Support
 
 - [Documentation](https://supatest.ai/docs)
-- [GitHub Issues](https://github.com/AvereSoftware/supatest/issues)
+- [GitHub Issues](https://github.com/supatest-ai/supatest/issues)
 
 ## License
 

package/dist/index.js

@@ -538,7 +538,7 @@ function getToolDisplayName(toolName) {
   };
   return displayNameMap[toolName] || toolName;
 }
-var AVAILABLE_MODELS, DEFAULT_MODEL_ID, DATE_SUFFIX_REGEX, CONTEXT_WINDOWS, util, objectUtil, ZodParsedType, getParsedType, ZodIssueCode, ZodError, errorMap, overrideErrorMap, makeIssue, ParseStatus, INVALID, DIRTY, OK, isAborted, isDirty, isValid, isAsync, errorUtil, ParseInputLazyPath, handleResult, ZodType, cuidRegex, cuid2Regex, ulidRegex, uuidRegex, nanoidRegex, jwtRegex, durationRegex, emailRegex, _emojiRegex, emojiRegex, ipv4Regex, ipv4CidrRegex, ipv6Regex, ipv6CidrRegex, base64Regex, base64urlRegex, dateRegexSource, dateRegex, ZodString, ZodNumber, ZodBigInt, ZodBoolean, ZodDate, ZodSymbol, ZodUndefined, ZodNull, ZodAny, ZodUnknown, ZodNever, ZodVoid, ZodArray, ZodObject, ZodUnion, getDiscriminator, ZodDiscriminatedUnion, ZodIntersection, ZodTuple, ZodRecord, ZodMap, ZodSet, ZodFunction, ZodLazy, ZodLiteral, ZodEnum, ZodNativeEnum, ZodPromise, ZodEffects, ZodOptional, ZodNullable, ZodDefault, ZodCatch, ZodNaN, ZodBranded, ZodPipeline, ZodReadonly, ZodFirstPartyTypeKind, stringType, numberType, booleanType, dateType, unknownType, arrayType, objectType, unionType, discriminatedUnionType, recordType, functionType, lazyType, literalType, enumType, promiseType, coerce, MAX_API_KEY_NAME_LENGTH, apiKeySchema, apiKeyUsageSchema, createApiKeyRequestSchema, apiKeyResponseSchema, apiKeyUsageSummarySchema, genericErrorSchema, validationErrorSchema, feedbackCategorySchema, FEEDBACK_CATEGORIES, createFeedbackSchema, feedbackResponseSchema, listFeedbackQuerySchema, feedbackListResponseSchema, healthMetricSchema, healthMetricDailyItemSchema, healthMetricsWithDailySchema, healthAnalyticsPeriodSchema, healthAnalyticsDailyItemSchema, healthAnalyticsResponseSchema, MAX_TIMEZONE_CHAR_LENGTH, organizationSchema, organizationSettingsSchema, textBlockSchema, toolUseBlockSchema, toolResultBlockSchema, thinkingBlockSchema, imageBlockSchema, contentBlockSchema, sessionSchema, createSessionRequestSchema, updateSessionRequestSchema, messageSchema, createMessageRequestSchema, cliEventSchema, createCLISessionRequestSchema, queryResultSchema, queryTurnSchema, queryContentSchema, queryUsageSchema, querySchema, runStatusSchema, testResultStatusSchema, testOutcomeSchema, attachmentKindSchema, stepCategorySchema, runSummarySchema, ciMetadataSchema, gitMetadataSchema, playwrightConfigSchema, errorInfoSchema, locationSchema, sourceSnippetSchema, runSchema, annotationSchema, testSchema, testResultSchema, baseStepSchema, stepSchema, attachmentSchema, listRunsQuerySchema, listTestsQuerySchema, runsListResponseSchema, runDetailResponseSchema, testsListResponseSchema, testDetailResponseSchema, testHistoryItemSchema, testHistoryResponseSchema, topOffenderSchema, topOffendersResponseSchema, trendPointSchema, trendsResponseSchema, errorCategorySchema, failureClusterSchema, newFailureSchema, runInsightsResponseSchema, FailureCategoryEnum, SelectorTypeEnum, FailureCategoryStatsSchema, FailureCategoriesResponseSchema, FailingSelectorStatsSchema, FailingSelectorsResponseSchema, newFailureItemSchema, newFailuresResponseSchema, flakyTestItemSchema, flakyTestsResponseSchema, slowestTestItemSchema, slowestTestsResponseSchema, runSummaryEmailFailureSchema, runSummaryEmailReportSchema, sendRunReportRequestSchema;
+var AVAILABLE_MODELS, DEFAULT_MODEL_ID, DATE_SUFFIX_REGEX, CONTEXT_WINDOWS, util, objectUtil, ZodParsedType, getParsedType, ZodIssueCode, ZodError, errorMap, overrideErrorMap, makeIssue, ParseStatus, INVALID, DIRTY, OK, isAborted, isDirty, isValid, isAsync, errorUtil, ParseInputLazyPath, handleResult, ZodType, cuidRegex, cuid2Regex, ulidRegex, uuidRegex, nanoidRegex, jwtRegex, durationRegex, emailRegex, _emojiRegex, emojiRegex, ipv4Regex, ipv4CidrRegex, ipv6Regex, ipv6CidrRegex, base64Regex, base64urlRegex, dateRegexSource, dateRegex, ZodString, ZodNumber, ZodBigInt, ZodBoolean, ZodDate, ZodSymbol, ZodUndefined, ZodNull, ZodAny, ZodUnknown, ZodNever, ZodVoid, ZodArray, ZodObject, ZodUnion, getDiscriminator, ZodDiscriminatedUnion, ZodIntersection, ZodTuple, ZodRecord, ZodMap, ZodSet, ZodFunction, ZodLazy, ZodLiteral, ZodEnum, ZodNativeEnum, ZodPromise, ZodEffects, ZodOptional, ZodNullable, ZodDefault, ZodCatch, ZodNaN, ZodBranded, ZodPipeline, ZodReadonly, ZodFirstPartyTypeKind, stringType, numberType, booleanType, dateType, unknownType, arrayType, objectType, unionType, discriminatedUnionType, recordType, functionType, lazyType, literalType, enumType, promiseType, coerce, MAX_API_KEY_NAME_LENGTH, apiKeySchema, apiKeyUsageSchema, createApiKeyRequestSchema, apiKeyResponseSchema, apiKeyUsageSummarySchema, genericErrorSchema, validationErrorSchema, feedbackCategorySchema, FEEDBACK_CATEGORIES, createFeedbackSchema, feedbackResponseSchema, listFeedbackQuerySchema, feedbackListResponseSchema, healthMetricSchema, healthMetricDailyItemSchema, healthMetricsWithDailySchema, healthAnalyticsPeriodSchema, healthAnalyticsDailyItemSchema, healthAnalyticsResponseSchema, MAX_TIMEZONE_CHAR_LENGTH, organizationSchema, organizationSettingsSchema, textBlockSchema, toolUseBlockSchema, toolResultBlockSchema, thinkingBlockSchema, imageBlockSchema, contentBlockSchema, sessionSchema, createSessionRequestSchema, updateSessionRequestSchema, messageSchema, createMessageRequestSchema, cliEventSchema, createCLISessionRequestSchema, queryResultSchema, queryTurnSchema, queryContentSchema, queryUsageSchema, querySchema, runStatusSchema, testResultStatusSchema, testOutcomeSchema, attachmentKindSchema, stepCategorySchema, runSummarySchema, ciMetadataSchema, gitMetadataSchema, playwrightConfigSchema, errorInfoSchema, locationSchema, sourceSnippetSchema, runSchema, annotationSchema, testSchema, testResultSchema, baseStepSchema, stepSchema, attachmentSchema, listRunsQuerySchema, listTestsQuerySchema, runsListResponseSchema, runDetailResponseSchema, testsListResponseSchema, testDetailResponseSchema, testHistoryItemSchema, testHistoryResponseSchema, topOffenderSchema, topOffendersResponseSchema, trendPointSchema, trendsResponseSchema, errorCategorySchema, failureClusterSchema, newFailureSchema, runInsightsResponseSchema, FailureCategoryEnum, SelectorTypeEnum, FailureCategoryStatsSchema, FailureCategoriesResponseSchema, FailingSelectorStatsSchema, FailingSelectorsResponseSchema, newFailureItemSchema, newFailuresResponseSchema, flakyTestItemSchema, flakyTestsResponseSchema, slowestTestItemSchema, slowestTestsResponseSchema, runSummaryEmailFailureSchema, runSummaryEmailReportSchema, sendRunReportRequestSchema, metricWithTrendSchema, weekOverWeekMetricsSchema, ciComputeTimeSchema, investigationCandidateSchema, failureCategoryBreakdownSchema, stabilityTrendSchema, folderStabilitySchema, managerReportSchema, managerReportQuerySchema, sendManagerReportRequestSchema, reportAttachmentLinkSchema, developerReportRegressionSchema, developerReportFlakyTestSchema, developerReportSlowTestSchema, developerRunSummaryReportSchema, executiveReportStatusSchema, executiveMetricSchema, executiveKeyMetricsSchema, executiveTrendPointSchema, executiveTrendsSchema, executiveFlakyOffenderSchema, executiveSlowestOffenderSchema, executiveTopOffendersSchema, executiveReportSchema, executiveReportQuerySchema, sendExecutiveReportRequestSchema;
 var init_shared_es = __esm({
   "../shared/dist/shared.es.mjs"() {
     "use strict";
@@ -5018,24 +5018,248 @@ var init_shared_es = __esm({
       startedAt: stringType(),
       endedAt: stringType().optional(),
       durationMs: numberType(),
-      // Git info
       branch: stringType().optional(),
       commit: stringType().optional(),
       commitMessage: stringType().optional(),
-      // Summary stats
       totalTests: numberType(),
       passedTests: numberType(),
       failedTests: numberType(),
       flakyTests: numberType(),
       skippedTests: numberType(),
       passRate: numberType(),
-      // Top failures
       topFailures: arrayType(runSummaryEmailFailureSchema)
     });
     sendRunReportRequestSchema = objectType({
       runId: stringType(),
       emails: arrayType(stringType().email())
     });
+    metricWithTrendSchema = objectType({
+      current: numberType(),
+      previous: numberType(),
+      change: numberType(),
+      percentChange: numberType().nullable()
+    });
+    weekOverWeekMetricsSchema = objectType({
+      passRate: metricWithTrendSchema,
+      flakyTestCount: metricWithTrendSchema,
+      newFailures: metricWithTrendSchema,
+      totalRuns: metricWithTrendSchema
+    });
+    ciComputeTimeSchema = objectType({
+      failedRunsMs: numberType(),
+      retriedRunsMs: numberType(),
+      totalWastedMs: numberType(),
+      failedRunsHours: numberType(),
+      retriedRunsHours: numberType(),
+      totalWastedHours: numberType()
+    });
+    investigationCandidateSchema = objectType({
+      testId: stringType(),
+      testRunId: stringType(),
+      runId: stringType(),
+      file: stringType(),
+      title: stringType(),
+      flakeCount: numberType(),
+      passRate: numberType(),
+      avgDurationMs: numberType(),
+      ciTimeImpactMs: numberType(),
+      ciTimeImpactHours: numberType(),
+      category: FailureCategoryEnum.nullable(),
+      firstFlakyAt: stringType().nullable()
+    });
+    failureCategoryBreakdownSchema = objectType({
+      category: FailureCategoryEnum,
+      count: numberType(),
+      percentage: numberType()
+    });
+    stabilityTrendSchema = enumType(["improving", "degrading", "stable"]);
+    folderStabilitySchema = objectType({
+      folder: stringType(),
+      passRate: numberType(),
+      previousPassRate: numberType(),
+      trend: stabilityTrendSchema,
+      testCount: numberType(),
+      failureCount: numberType()
+    });
+    managerReportSchema = objectType({
+      period: objectType({
+        start: stringType(),
+        end: stringType(),
+        days: numberType()
+      }),
+      weekOverWeek: weekOverWeekMetricsSchema,
+      ciComputeTime: ciComputeTimeSchema,
+      investigationCandidates: arrayType(investigationCandidateSchema),
+      failureCategories: arrayType(failureCategoryBreakdownSchema),
+      folderStability: arrayType(folderStabilitySchema)
+    });
+    managerReportQuerySchema = objectType({
+      startDate: stringType().regex(
+        /^\d{4}-\d{2}-\d{2}(T\d{2}:\d{2}:\d{2}(\.\d{3})?Z?)?$/,
+        "startDate must be in format YYYY-MM-DD or ISO datetime"
+      ),
+      endDate: stringType().regex(
+        /^\d{4}-\d{2}-\d{2}(T\d{2}:\d{2}:\d{2}(\.\d{3})?Z?)?$/,
+        "endDate must be in format YYYY-MM-DD or ISO datetime"
+      )
+    });
+    sendManagerReportRequestSchema = objectType({
+      startDate: stringType(),
+      endDate: stringType(),
+      emails: arrayType(stringType().email())
+    });
+    reportAttachmentLinkSchema = objectType({
+      name: stringType(),
+      kind: attachmentKindSchema,
+      url: stringType().optional()
+    });
+    developerReportRegressionSchema = objectType({
+      testRunId: stringType(),
+      testId: stringType(),
+      title: stringType(),
+      file: stringType(),
+      errorMessage: stringType().nullable(),
+      errorStack: stringType().nullable(),
+      aiSummary: stringType().nullable(),
+      attachments: arrayType(reportAttachmentLinkSchema),
+      lastStableRun: objectType({
+        runId: stringType(),
+        date: stringType(),
+        branch: stringType().optional()
+      }).nullable()
+    });
+    developerReportFlakyTestSchema = objectType({
+      testRunId: stringType(),
+      testId: stringType(),
+      title: stringType(),
+      file: stringType(),
+      passRate: numberType(),
+      category: errorCategorySchema.nullable(),
+      lastPassedRun: objectType({
+        runId: stringType(),
+        date: stringType()
+      }).nullable()
+    });
+    developerReportSlowTestSchema = objectType({
+      testRunId: stringType(),
+      testId: stringType(),
+      title: stringType(),
+      file: stringType(),
+      durationMs: numberType(),
+      historicalAvgMs: numberType(),
+      slowdownFactor: numberType()
+      // how many times slower than average
+    });
+    developerRunSummaryReportSchema = objectType({
+      runId: stringType(),
+      readableId: stringType().optional(),
+      runDetailsUrl: stringType(),
+      startedAt: stringType(),
+      endedAt: stringType().optional(),
+      durationMs: numberType(),
+      branch: stringType().optional(),
+      commit: stringType().optional(),
+      commitMessage: stringType().optional(),
+      // Summary counts
+      totalTests: numberType(),
+      passedTests: numberType(),
+      failedTests: numberType(),
+      flakyTests: numberType(),
+      skippedTests: numberType(),
+      passRate: numberType(),
+      // Sections
+      newRegressions: arrayType(developerReportRegressionSchema),
+      knownFlaky: arrayType(developerReportFlakyTestSchema),
+      slowTests: arrayType(developerReportSlowTestSchema)
+    });
+    executiveReportStatusSchema = enumType([
+      "healthy",
+      "needs_attention",
+      "critical"
+    ]);
+    executiveMetricSchema = objectType({
+      /** Current month's value */
+      value: numberType(),
+      /** Previous month's value */
+      previousValue: numberType(),
+      /** Percentage change from previous month (null if previous was 0) */
+      change: numberType().nullable()
+    });
+    executiveKeyMetricsSchema = objectType({
+      /** CI First-Try Pass Rate: COUNT(runs WHERE failed=0 AND flaky=0) / COUNT(runs) */
+      ciFirstTryPassRate: executiveMetricSchema,
+      /** Total Test Pass Rate from health analytics */
+      testPassRate: executiveMetricSchema,
+      /** Count of distinct tests with flaky outcomes */
+      flakyTestCount: executiveMetricSchema,
+      /** CI compute time lost on failed/retried runs in hours */
+      ciComputeLostHours: executiveMetricSchema
+    });
+    executiveTrendPointSchema = objectType({
+      date: stringType(),
+      value: numberType()
+    });
+    executiveTrendsSchema = objectType({
+      /** Daily pass rate values for sparkline */
+      dailyPassRate: arrayType(executiveTrendPointSchema),
+      /** Daily flaky count values for sparkline */
+      dailyFlakyCount: arrayType(executiveTrendPointSchema)
+    });
+    executiveFlakyOffenderSchema = objectType({
+      testId: stringType(),
+      title: stringType(),
+      file: stringType(),
+      /** Number of flaky occurrences */
+      flakyCount: numberType(),
+      /** CI time impact in hours */
+      ciTimeImpactHours: numberType()
+    });
+    executiveSlowestOffenderSchema = objectType({
+      testId: stringType(),
+      title: stringType(),
+      file: stringType(),
+      /** Average duration in milliseconds */
+      avgDurationMs: numberType(),
+      /** Trend percentage change from previous period (null if no previous data) */
+      trend: numberType().nullable()
+    });
+    executiveTopOffendersSchema = objectType({
+      /** Top 3 most flaky tests with CI time impact */
+      mostFlaky: arrayType(executiveFlakyOffenderSchema),
+      /** Top 3 slowest tests with trend */
+      slowest: arrayType(executiveSlowestOffenderSchema)
+    });
+    executiveReportSchema = objectType({
+      /** Month in format YYYY-MM */
+      month: stringType(),
+      /** When the report was generated */
+      generatedAt: stringType(),
+      /** URL to view full report in dashboard */
+      reportUrl: stringType(),
+      /** Overall status: healthy, needs_attention, or critical */
+      status: executiveReportStatusSchema,
+      /** 4 key metrics with month-over-month comparison */
+      keyMetrics: executiveKeyMetricsSchema,
+      /** 30-day trend data for sparklines */
+      trends: executiveTrendsSchema,
+      /** Top offenders (most flaky and slowest tests) */
+      topOffenders: executiveTopOffendersSchema,
+      /** Auto-generated signal messages based on thresholds */
+      signals: arrayType(stringType())
+    });
+    executiveReportQuerySchema = objectType({
+      month: stringType().regex(
+        /^\d{4}-\d{2}$/,
+        "month must be in format YYYY-MM"
+      )
+    });
+    sendExecutiveReportRequestSchema = objectType({
+      month: stringType().regex(
+        /^\d{4}-\d{2}$/,
+        "month must be in format YYYY-MM"
+      ),
+      emails: arrayType(stringType().email())
+    });
   }
 });
 
@@ -5072,7 +5296,9 @@ function getPlaywrightVersion() {
   try {
     const result = spawnSync("npx", ["playwright", "--version"], {
       encoding: "utf-8",
-      stdio: ["ignore", "pipe", "ignore"]
+      stdio: ["ignore", "pipe", "ignore"],
+      shell: true
+      // Required for Windows where npx is npx.cmd
     });
     if (result.status === 0 && result.stdout) {
       return result.stdout.trim().replace("Version ", "");
@@ -5140,7 +5366,9 @@ function installChromium() {
   console.log("");
   try {
     const result = spawnSync("npx", ["playwright", "install", "chromium"], {
-      stdio: "inherit"
+      stdio: "inherit",
+      shell: true
+      // Required for Windows where npx is npx.cmd
     });
     if (result.status === 0) {
       return {
@@ -5294,7 +5522,7 @@ var CLI_VERSION;
 var init_version = __esm({
   "src/version.ts"() {
     "use strict";
-    CLI_VERSION = "0.0.28";
+    CLI_VERSION = "0.0.30";
   }
 });
 
@@ -8317,7 +8545,8 @@ function openBrowser(url) {
     default:
       command = "xdg-open";
   }
-  spawn2(command, [url], { detached: true, stdio: "ignore" }).unref();
+  const options = { detached: true, stdio: "ignore", shell: os3 === "win32" };
+  spawn2(command, [url], options).unref();
 }
 function startCallbackServer(port, expectedState) {
   return new Promise((resolve2, reject) => {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@supatest/cli",
-  "version": "0.0.28",
+  "version": "0.0.30",
   "description": "Supatest CLI - AI-powered task automation for CI/CD",
   "type": "module",
   "bin": {