agentic-qe 3.7.7 → 3.7.9

package/.claude/helpers/statusline-v3.cjs

@@ -308,7 +308,19 @@ function getLearningMetrics(projectDir) {
   // V3 trajectories (new V3 trajectory tracking)
   const trajectories = parseInt(sqlite3Query(dbPath, 'SELECT COUNT(*) FROM qe_trajectories')) || 0;
   // Captured experiences (task execution captures)
-  const capturedExp = parseInt(sqlite3Query(dbPath, 'SELECT COUNT(*) FROM captured_experiences')) || 0;
+  // Use SUM(consolidation_count) for monotonically non-decreasing counter:
+  // - New experience → +1
+  // - Merge A into B → A excluded (consolidated_into set), B's count += A's count → net 0
+  // - Archive → row stays, still counted → net 0
+  // Falls back to COUNT(*) if consolidation columns not yet added
+  let capturedExp = 0;
+  const consolidatedQuery = sqlite3Query(dbPath,
+    "SELECT COALESCE(SUM(consolidation_count), COUNT(*)) FROM captured_experiences WHERE consolidated_into IS NULL OR consolidated_into = 'archived'", '__FAIL__');
+  if (consolidatedQuery !== '__FAIL__') {
+    capturedExp = parseInt(consolidatedQuery) || 0;
+  } else {
+    capturedExp = parseInt(sqlite3Query(dbPath, 'SELECT COUNT(*) FROM captured_experiences')) || 0;
+  }
   // Memory entries with learning data (MCP-stored experiences)
   const memoryLearning = parseInt(sqlite3Query(dbPath, "SELECT COUNT(*) FROM memory_entries WHERE key LIKE 'learning%' OR key LIKE 'phase2/learning%'")) || 0;
   // QE pattern usage (hook-recorded outcomes from aqe hooks post-task/post-edit)

package/.claude/skills/debug-loop/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: debug-loop
 description: Hypothesis-driven autonomous debugging with real command validation
-trust_tier: 3
+trust_tier: 0
 domain: debugging
 ---
 

package/.claude/skills/enterprise-integration-testing/evals/enterprise-integration-testing.yaml

@@ -0,0 +1,158 @@
+skill: enterprise-integration-testing
+version: 1.0.0
+description: >
+  Evaluation suite for enterprise integration testing orchestration.
+  Tests SAP-specific patterns (RFC, BAPI, IDoc, OData, Fiori), cross-system
+  data validation, middleware testing, and enterprise quality gates.
+
+models_to_test:
+  - claude-3.5-sonnet
+  - claude-3-haiku
+
+mcp_integration:
+  enabled: true
+  namespace: skill-validation
+  query_patterns: true
+  track_outcomes: true
+  store_patterns: true
+  target_agents:
+    - qe-learning-coordinator
+    - qe-queen-coordinator
+
+learning:
+  store_success_patterns: true
+  pattern_ttl_days: 90
+
+result_format:
+  json_output: true
+  include_timing: true
+  include_token_usage: true
+
+setup:
+  required_tools:
+    - jq
+
+test_cases:
+
+  - id: tc001_sap_rfc_testing
+    description: "Generate SAP RFC/BAPI integration test strategy"
+    category: sap
+    priority: critical
+
+    input:
+      prompt: |
+        Generate test strategy for SAP RFC integration that processes
+        purchase orders via BAPI_PO_CREATE1 and validates material
+        availability through BAPI_MATERIAL_AVAILABILITY.
+      context:
+        language: typescript
+        framework: sap-integration
+
+    expected_output:
+      must_contain:
+        - "RFC"
+        - "BAPI"
+        - "purchase order"
+        - "test"
+
+    validation:
+      schema_check: true
+      keyword_match_threshold: 0.8
+
+  - id: tc002_idoc_message_testing
+    description: "Generate IDoc message flow test strategy"
+    category: sap
+    priority: critical
+
+    input:
+      prompt: |
+        Create test strategy for IDoc-based order-to-cash flow:
+        ORDERS05 IDoc from e-commerce to SAP, DESADV IDoc for shipping,
+        INVOIC02 IDoc for billing.
+      context:
+        language: typescript
+
+    expected_output:
+      must_contain:
+        - "IDoc"
+        - "message"
+        - "validation"
+
+    validation:
+      schema_check: true
+
+  - id: tc003_odata_contract_testing
+    description: "Generate OData service contract tests"
+    category: odata
+    priority: high
+
+    input:
+      prompt: |
+        Create contract tests for SAP OData service /sap/opu/odata/sap/API_SALES_ORDER_SRV
+        that validates entity sets, navigation properties, and filter operations.
+      context:
+        language: typescript
+
+    expected_output:
+      must_contain:
+        - "OData"
+        - "contract"
+        - "entity"
+
+    validation:
+      schema_check: true
+
+  - id: tc004_cross_system_validation
+    description: "Generate cross-system data consistency tests"
+    category: cross-system
+    priority: high
+
+    input:
+      prompt: |
+        Generate tests to validate data consistency between SAP ERP,
+        Salesforce CRM, and PostgreSQL data warehouse for customer master data.
+      context:
+        framework: enterprise
+
+    expected_output:
+      must_contain:
+        - "consistency"
+        - "validation"
+        - "data"
+
+    validation:
+      schema_check: true
+
+  - id: tc005_enterprise_quality_gate
+    description: "Enforce enterprise integration quality gates"
+    category: quality-gate
+    priority: high
+
+    input:
+      metrics:
+        idoc_success_rate: 98.5
+        rfc_latency_p99_ms: 2500
+        data_consistency: 99.2
+        error_handling_coverage: 85
+
+    expected_output:
+      must_contain:
+        - "quality"
+        - "gate"
+
+    validation:
+      schema_check: true
+
+success_criteria:
+  pass_rate: 0.9
+  critical_pass_rate: 1.0
+  avg_reasoning_quality: 0.75
+  max_execution_time_ms: 300000
+
+metadata:
+  author: "qe-enterprise-orchestrator"
+  created: "2026-03-05"
+  coverage_target: >
+    Enterprise integration testing with 5 test cases covering SAP RFC/BAPI,
+    IDoc message flows, OData contract testing, cross-system validation,
+    and enterprise quality gates.

package/.claude/skills/enterprise-integration-testing/schemas/output.json

@@ -0,0 +1,74 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://agentic-qe.dev/schemas/enterprise-integration-testing-output.json",
+  "title": "Enterprise Integration Testing Output Schema",
+  "description": "Schema for enterprise integration testing output. Covers SAP, middleware, WMS, and cross-system validation.",
+  "type": "object",
+  "required": ["skillName", "version", "timestamp", "status", "trustTier", "output"],
+  "properties": {
+    "skillName": {
+      "type": "string",
+      "const": "enterprise-integration-testing"
+    },
+    "version": {
+      "type": "string",
+      "pattern": "^\\d+\\.\\d+\\.\\d+(-[a-zA-Z0-9]+)?$"
+    },
+    "timestamp": {
+      "type": "string",
+      "format": "date-time"
+    },
+    "status": {
+      "type": "string",
+      "enum": ["success", "partial", "failed", "skipped"]
+    },
+    "trustTier": {
+      "type": "integer",
+      "const": 3
+    },
+    "output": {
+      "type": "object",
+      "required": ["summary", "testStrategy", "systemsCovered"],
+      "properties": {
+        "summary": {
+          "type": "string",
+          "minLength": 100
+        },
+        "testStrategy": {
+          "type": "object",
+          "properties": {
+            "approach": { "type": "string" },
+            "testLayers": { "type": "array", "items": { "type": "string" } },
+            "integrationPoints": { "type": "array", "items": { "type": "string" } }
+          }
+        },
+        "systemsCovered": {
+          "type": "array",
+          "items": { "type": "string" }
+        },
+        "sapTesting": {
+          "type": "object",
+          "properties": {
+            "rfcTests": { "type": "array", "items": { "type": "object" } },
+            "idocTests": { "type": "array", "items": { "type": "object" } },
+            "odataTests": { "type": "array", "items": { "type": "object" } }
+          }
+        },
+        "crossSystemValidation": {
+          "type": "object",
+          "properties": {
+            "consistencyChecks": { "type": "array", "items": { "type": "string" } },
+            "dataFlowTests": { "type": "array", "items": { "type": "string" } }
+          }
+        },
+        "qualityGates": {
+          "type": "object",
+          "properties": {
+            "passed": { "type": "boolean" },
+            "gates": { "type": "array", "items": { "type": "object" } }
+          }
+        }
+      }
+    }
+  }
+}

package/.claude/skills/enterprise-integration-testing/scripts/validate-config.json

@@ -0,0 +1,25 @@
+{
+  "skillName": "enterprise-integration-testing",
+  "skillVersion": "1.0.0",
+  "requiredTools": [
+    "jq"
+  ],
+  "optionalTools": [],
+  "schemaPath": "schemas/output.json",
+  "requiredFields": [
+    "skillName",
+    "status",
+    "output"
+  ],
+  "requiredNonEmptyFields": [],
+  "mustContainTerms": [],
+  "mustNotContainTerms": [],
+  "enumValidations": {
+    ".status": [
+      "success",
+      "partial",
+      "failed",
+      "skipped"
+    ]
+  }
+}

package/.claude/skills/middleware-testing-patterns/evals/middleware-testing-patterns.yaml

@@ -0,0 +1,153 @@
+skill: middleware-testing-patterns
+version: 1.0.0
+description: >
+  Evaluation suite for enterprise middleware testing patterns.
+  Tests message routing, transformation, DLQ handling, protocol mediation,
+  ESB error handling, and Enterprise Integration Patterns.
+
+models_to_test:
+  - claude-3.5-sonnet
+  - claude-3-haiku
+
+mcp_integration:
+  enabled: true
+  namespace: skill-validation
+  query_patterns: true
+  track_outcomes: true
+  store_patterns: true
+  target_agents:
+    - qe-learning-coordinator
+    - qe-queen-coordinator
+
+learning:
+  store_success_patterns: true
+  pattern_ttl_days: 90
+
+result_format:
+  json_output: true
+  include_timing: true
+  include_token_usage: true
+
+setup:
+  required_tools:
+    - jq
+
+test_cases:
+
+  - id: tc001_message_routing_test
+    description: "Generate tests for content-based message routing"
+    category: routing
+    priority: critical
+
+    input:
+      prompt: |
+        Generate test strategy for content-based router that routes
+        order messages to fulfillment (type=physical), digital delivery
+        (type=digital), or subscription service (type=recurring).
+      context:
+        framework: rabbitmq
+
+    expected_output:
+      must_contain:
+        - "routing"
+        - "message"
+        - "test"
+
+    validation:
+      schema_check: true
+      keyword_match_threshold: 0.8
+
+  - id: tc002_message_transformation
+    description: "Test message transformation and mapping correctness"
+    category: transformation
+    priority: critical
+
+    input:
+      prompt: |
+        Create tests for XML-to-JSON transformation pipeline that converts
+        SAP IDoc XML into REST API JSON payloads, validating field mapping,
+        data type conversion, and null handling.
+
+    expected_output:
+      must_contain:
+        - "transform"
+        - "mapping"
+        - "validation"
+
+    validation:
+      schema_check: true
+
+  - id: tc003_dlq_handling
+    description: "Test dead letter queue processing and retry logic"
+    category: dlq
+    priority: critical
+
+    input:
+      prompt: |
+        Generate tests for DLQ handling: messages that fail 3 retries
+        with exponential backoff should land in DLQ, be parseable for
+        root cause, and support manual replay.
+      context:
+        framework: kafka
+
+    expected_output:
+      must_contain:
+        - "dead letter"
+        - "retry"
+        - "backoff"
+
+    validation:
+      schema_check: true
+
+  - id: tc004_protocol_mediation
+    description: "Test protocol mediation between different transports"
+    category: mediation
+    priority: high
+
+    input:
+      prompt: |
+        Create tests for protocol mediation layer that bridges
+        SOAP/XML services to REST/JSON APIs, including WSDL validation,
+        header mapping, and fault translation.
+
+    expected_output:
+      must_contain:
+        - "protocol"
+        - "mediation"
+        - "SOAP"
+
+    validation:
+      schema_check: true
+
+  - id: tc005_eip_patterns
+    description: "Test Enterprise Integration Patterns implementation"
+    category: eip
+    priority: high
+
+    input:
+      prompt: |
+        Generate tests for EIP patterns: Aggregator (collect 10 messages
+        within 30s window), Splitter (break batch into individual items),
+        and Scatter-Gather (fan-out to 3 services, merge responses).
+
+    expected_output:
+      must_contain:
+        - "aggregator"
+        - "splitter"
+        - "pattern"
+
+    validation:
+      schema_check: true
+
+success_criteria:
+  pass_rate: 0.9
+  critical_pass_rate: 1.0
+  avg_reasoning_quality: 0.75
+  max_execution_time_ms: 300000
+
+metadata:
+  author: "qe-middleware-orchestrator"
+  created: "2026-03-05"
+  coverage_target: >
+    Middleware testing patterns with 5 test cases covering message routing,
+    transformation, DLQ handling, protocol mediation, and EIP patterns.

package/.claude/skills/middleware-testing-patterns/schemas/output.json

@@ -0,0 +1,58 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://agentic-qe.dev/schemas/middleware-testing-patterns-output.json",
+  "title": "Middleware Testing Patterns Output Schema",
+  "description": "Schema for middleware testing output. Covers message routing, transformation, DLQ, protocol mediation, and EIP patterns.",
+  "type": "object",
+  "required": ["skillName", "version", "timestamp", "status", "trustTier", "output"],
+  "properties": {
+    "skillName": {
+      "type": "string",
+      "const": "middleware-testing-patterns"
+    },
+    "version": {
+      "type": "string",
+      "pattern": "^\\d+\\.\\d+\\.\\d+(-[a-zA-Z0-9]+)?$"
+    },
+    "timestamp": {
+      "type": "string",
+      "format": "date-time"
+    },
+    "status": {
+      "type": "string",
+      "enum": ["success", "partial", "failed", "skipped"]
+    },
+    "trustTier": {
+      "type": "integer",
+      "const": 3
+    },
+    "output": {
+      "type": "object",
+      "required": ["summary", "testStrategy"],
+      "properties": {
+        "summary": {
+          "type": "string",
+          "minLength": 100
+        },
+        "testStrategy": {
+          "type": "object",
+          "properties": {
+            "routingTests": { "type": "array", "items": { "type": "object" } },
+            "transformationTests": { "type": "array", "items": { "type": "object" } },
+            "dlqTests": { "type": "array", "items": { "type": "object" } },
+            "mediationTests": { "type": "array", "items": { "type": "object" } },
+            "eipTests": { "type": "array", "items": { "type": "object" } }
+          }
+        },
+        "findings": {
+          "type": "array",
+          "items": { "type": "object" }
+        },
+        "recommendations": {
+          "type": "array",
+          "items": { "type": "string" }
+        }
+      }
+    }
+  }
+}

package/.claude/skills/middleware-testing-patterns/scripts/validate-config.json

@@ -0,0 +1,25 @@
+{
+  "skillName": "middleware-testing-patterns",
+  "skillVersion": "1.0.0",
+  "requiredTools": [
+    "jq"
+  ],
+  "optionalTools": [],
+  "schemaPath": "schemas/output.json",
+  "requiredFields": [
+    "skillName",
+    "status",
+    "output"
+  ],
+  "requiredNonEmptyFields": [],
+  "mustContainTerms": [],
+  "mustNotContainTerms": [],
+  "enumValidations": {
+    ".status": [
+      "success",
+      "partial",
+      "failed",
+      "skipped"
+    ]
+  }
+}

package/.claude/skills/observability-testing-patterns/evals/observability-testing-patterns.yaml

@@ -0,0 +1,157 @@
+skill: observability-testing-patterns
+version: 1.0.0
+description: >
+  Evaluation suite for observability and monitoring validation patterns.
+  Tests dashboard accuracy, alerting rules, log aggregation, APM traces,
+  and SLA/SLO verification.
+
+models_to_test:
+  - claude-3.5-sonnet
+  - claude-3-haiku
+
+mcp_integration:
+  enabled: true
+  namespace: skill-validation
+  query_patterns: true
+  track_outcomes: true
+  store_patterns: true
+  target_agents:
+    - qe-learning-coordinator
+    - qe-queen-coordinator
+
+learning:
+  store_success_patterns: true
+  pattern_ttl_days: 90
+
+result_format:
+  json_output: true
+  include_timing: true
+  include_token_usage: true
+
+setup:
+  required_tools:
+    - jq
+
+test_cases:
+
+  - id: tc001_dashboard_validation
+    description: "Validate monitoring dashboard accuracy and completeness"
+    category: dashboard
+    priority: critical
+
+    input:
+      prompt: |
+        Generate test strategy for validating a Grafana dashboard that monitors
+        API response times, error rates, and throughput for a microservices architecture.
+      context:
+        framework: grafana
+
+    expected_output:
+      must_contain:
+        - "dashboard"
+        - "metric"
+        - "validation"
+
+    validation:
+      schema_check: true
+      keyword_match_threshold: 0.8
+
+  - id: tc002_alert_rule_testing
+    description: "Test alerting rules fire correctly under conditions"
+    category: alerting
+    priority: critical
+
+    input:
+      prompt: |
+        Create tests for PagerDuty alert rules:
+        - P1: error_rate > 5% for 2 minutes
+        - P2: p99_latency > 2000ms for 5 minutes
+        - P3: disk_usage > 85%
+      context:
+        framework: pagerduty
+
+    expected_output:
+      must_contain:
+        - "alert"
+        - "threshold"
+        - "trigger"
+
+    validation:
+      schema_check: true
+
+  - id: tc003_log_aggregation_testing
+    description: "Validate log aggregation pipeline correctness"
+    category: logging
+    priority: high
+
+    input:
+      prompt: |
+        Generate tests for ELK stack log pipeline ensuring structured logs
+        from 15 microservices are correctly parsed, indexed, and searchable
+        with correlation IDs.
+      context:
+        framework: elasticsearch
+
+    expected_output:
+      must_contain:
+        - "log"
+        - "aggregation"
+        - "correlation"
+
+    validation:
+      schema_check: true
+
+  - id: tc004_apm_trace_validation
+    description: "Validate distributed tracing across services"
+    category: tracing
+    priority: high
+
+    input:
+      prompt: |
+        Create test strategy for validating OpenTelemetry distributed traces
+        across API gateway → auth service → order service → payment service.
+
+    expected_output:
+      must_contain:
+        - "trace"
+        - "span"
+        - "distributed"
+
+    validation:
+      schema_check: true
+
+  - id: tc005_slo_verification
+    description: "Verify SLO/SLA compliance measurement accuracy"
+    category: slo
+    priority: critical
+
+    input:
+      prompt: |
+        Generate tests to verify SLO measurement accuracy:
+        - Availability SLO: 99.95% (error budget: 21.9 min/month)
+        - Latency SLO: p99 < 500ms
+        - Throughput SLO: > 10,000 RPS
+      context:
+        framework: prometheus
+
+    expected_output:
+      must_contain:
+        - "SLO"
+        - "error budget"
+        - "compliance"
+
+    validation:
+      schema_check: true
+
+success_criteria:
+  pass_rate: 0.9
+  critical_pass_rate: 1.0
+  avg_reasoning_quality: 0.75
+  max_execution_time_ms: 300000
+
+metadata:
+  author: "qe-observability-orchestrator"
+  created: "2026-03-05"
+  coverage_target: >
+    Observability testing patterns with 5 test cases covering dashboard validation,
+    alert rule testing, log aggregation, APM trace validation, and SLO verification.