ma-agents 2.19.2 → 2.20.0

package/lib/bmad-cache/tea/src/workflows/testarch/bmad-testarch-nfr/steps-c/step-04c-subagent-reliability.md

@@ -0,0 +1,85 @@
+---
+name: 'step-04c-subagent-reliability'
+description: 'Subagent: Reliability NFR assessment'
+subagent: true
+outputFile: '/tmp/tea-nfr-reliability-{{timestamp}}.json'
+---
+
+# Subagent 4C: Reliability NFR Assessment
+
+## SUBAGENT CONTEXT
+
+This is an **isolated subagent** running in parallel with other NFR domain assessments.
+
+**Your task:** Assess RELIABILITY NFR domain only.
+
+---
+
+## SUBAGENT TASK
+
+### 1. Reliability Assessment Categories
+
+**A) Error Handling:**
+
+- Try-catch blocks for critical operations
+- Graceful degradation
+- Circuit breakers
+- Retry mechanisms
+
+**B) Monitoring & Observability:**
+
+- Logging implementation
+- Error tracking (Sentry/Datadog)
+- Health check endpoints
+- Alerting systems
+
+**C) Fault Tolerance:**
+
+- Database failover
+- Service redundancy
+- Backup strategies
+- Disaster recovery plan
+
+**D) Uptime & Availability:**
+
+- SLA targets
+- Historical uptime
+- Incident response
+
+---
+
+## OUTPUT FORMAT
+
+```json
+{
+  "domain": "reliability",
+  "risk_level": "LOW",
+  "findings": [
+    {
+      "category": "Error Handling",
+      "status": "PASS",
+      "description": "Comprehensive error handling with circuit breakers",
+      "evidence": ["Circuit breaker pattern in src/services/", "Retry logic implemented"],
+      "recommendations": []
+    },
+    {
+      "category": "Monitoring",
+      "status": "CONCERN",
+      "description": "No APM (Application Performance Monitoring) tool",
+      "evidence": ["Logging present but no distributed tracing"],
+      "recommendations": ["Implement APM (Datadog/New Relic)", "Add distributed tracing"]
+    }
+  ],
+  "compliance": {
+    "SLA_99.9": "PASS"
+  },
+  "priority_actions": ["Implement APM for better observability"],
+  "summary": "Reliability is good with minor monitoring gaps"
+}
+```
+
+---
+
+## EXIT CONDITION
+
+Subagent completes when JSON output written to temp file.

package/lib/bmad-cache/tea/src/workflows/testarch/bmad-testarch-nfr/steps-c/step-04d-subagent-scalability.md

@@ -0,0 +1,88 @@
+---
+name: 'step-04d-subagent-scalability'
+description: 'Subagent: Scalability NFR assessment'
+subagent: true
+outputFile: '/tmp/tea-nfr-scalability-{{timestamp}}.json'
+---
+
+# Subagent 4D: Scalability NFR Assessment
+
+## SUBAGENT CONTEXT
+
+This is an **isolated subagent** running in parallel with other NFR domain assessments.
+
+**Your task:** Assess SCALABILITY NFR domain only.
+
+---
+
+## SUBAGENT TASK
+
+### 1. Scalability Assessment Categories
+
+**A) Horizontal Scaling:**
+
+- Stateless architecture
+- Load balancer configuration
+- Container orchestration (K8s)
+- Auto-scaling policies
+
+**B) Vertical Scaling:**
+
+- Resource allocation
+- Database size limits
+- Memory management
+- CPU optimization
+
+**C) Data Scaling:**
+
+- Database partitioning/sharding
+- Read replicas
+- Caching layers
+- Data archival strategy
+
+**D) Traffic Handling:**
+
+- CDN for static assets
+- Rate limiting
+- Queue systems for async work
+- WebSocket scaling
+
+---
+
+## OUTPUT FORMAT
+
+```json
+{
+  "domain": "scalability",
+  "risk_level": "MEDIUM",
+  "findings": [
+    {
+      "category": "Horizontal Scaling",
+      "status": "PASS",
+      "description": "Stateless architecture with container orchestration",
+      "evidence": ["Docker + Kubernetes setup", "Auto-scaling configured"],
+      "recommendations": []
+    },
+    {
+      "category": "Data Scaling",
+      "status": "CONCERN",
+      "description": "No database sharding strategy for large data growth",
+      "evidence": ["Single database instance", "No partitioning"],
+      "recommendations": ["Plan database sharding strategy", "Implement read replicas", "Consider database clustering"]
+    }
+  ],
+  "compliance": {
+    "1M_users": "PASS",
+    "10M_users": "CONCERN",
+    "100M_users": "FAIL"
+  },
+  "priority_actions": ["Design database sharding strategy for future growth", "Implement read replicas for read-heavy workloads"],
+  "summary": "Scalability is good up to 1M users, concerns for 10M+ users"
+}
+```
+
+---
+
+## EXIT CONDITION
+
+Subagent completes when JSON output written to temp file.

package/lib/bmad-cache/tea/src/workflows/testarch/bmad-testarch-nfr/steps-c/step-04e-aggregate-nfr.md

@@ -0,0 +1,264 @@
+---
+name: 'step-04e-aggregate-nfr'
+description: 'Aggregate NFR domain assessments into executive summary'
+nextStepFile: './step-05-generate-report.md'
+outputFile: '{test_artifacts}/nfr-assessment.md'
+---
+
+# Step 4E: Aggregate NFR Assessment Results
+
+## STEP GOAL
+
+Read outputs from 4 parallel NFR subagents, calculate overall risk level, aggregate compliance status, and identify cross-domain risks.
+
+---
+
+## MANDATORY EXECUTION RULES
+
+- 📖 Read the entire step file before acting
+- ✅ Speak in `{communication_language}`
+- ✅ Read all 4 subagent outputs
+- ✅ Calculate overall risk level
+- ❌ Do NOT re-assess NFRs (use subagent outputs)
+
+---
+
+## MANDATORY SEQUENCE
+
+### 1. Read All Subagent Outputs
+
+```javascript
+const domains = ['security', 'performance', 'reliability', 'scalability'];
+const assessments = {};
+
+domains.forEach((domain) => {
+  const outputPath = `/tmp/tea-nfr-${domain}-{{timestamp}}.json`;
+  assessments[domain] = JSON.parse(fs.readFileSync(outputPath, 'utf8'));
+});
+```
+
+---
+
+### 2. Calculate Overall Risk Level
+
+**Risk hierarchy:** HIGH > MEDIUM > LOW > NONE
+
+```javascript
+const riskLevels = { HIGH: 3, MEDIUM: 2, LOW: 1, NONE: 0 };
+const domainRisks = domains.map((d) => assessments[d].risk_level);
+const maxRiskValue = Math.max(...domainRisks.map((r) => riskLevels[r]));
+const overallRisk = Object.keys(riskLevels).find((k) => riskLevels[k] === maxRiskValue);
+```
+
+**Risk assessment:**
+
+- If ANY domain is HIGH → overall is HIGH
+- If ANY domain is MEDIUM (and none HIGH) → overall is MEDIUM
+- If ALL domains are LOW/NONE → overall is LOW
+
+---
+
+### 3. Aggregate Compliance Status
+
+```javascript
+const allCompliance = {};
+
+domains.forEach((domain) => {
+  const compliance = assessments[domain].compliance;
+  Object.entries(compliance).forEach(([standard, status]) => {
+    if (!allCompliance[standard]) {
+      allCompliance[standard] = [];
+    }
+    allCompliance[standard].push({ domain, status });
+  });
+});
+
+// Determine overall compliance per standard
+const complianceSummary = {};
+Object.entries(allCompliance).forEach(([standard, statuses]) => {
+  const hasFail = statuses.some((s) => s.status === 'FAIL');
+  const hasPartial = statuses.some((s) => s.status === 'PARTIAL' || s.status === 'CONCERN');
+
+  complianceSummary[standard] = hasFail ? 'FAIL' : hasPartial ? 'PARTIAL' : 'PASS';
+});
+```
+
+---
+
+### 4. Identify Cross-Domain Risks
+
+**Look for risks that span multiple domains:**
+
+```javascript
+const crossDomainRisks = [];
+
+// Example: Performance + Scalability issue
+const perfConcerns = assessments.performance.findings.filter((f) => f.status !== 'PASS');
+const scaleConcerns = assessments.scalability.findings.filter((f) => f.status !== 'PASS');
+if (perfConcerns.length > 0 && scaleConcerns.length > 0) {
+  crossDomainRisks.push({
+    domains: ['performance', 'scalability'],
+    description: 'Performance issues may worsen under scale',
+    impact: 'HIGH',
+  });
+}
+
+// Example: Security + Reliability issue
+const securityFails = assessments.security.findings.filter((f) => f.status === 'FAIL');
+const reliabilityConcerns = assessments.reliability.findings.filter((f) => f.status !== 'PASS');
+if (securityFails.length > 0 && reliabilityConcerns.length > 0) {
+  crossDomainRisks.push({
+    domains: ['security', 'reliability'],
+    description: 'Security vulnerabilities may cause reliability incidents',
+    impact: 'CRITICAL',
+  });
+}
+```
+
+---
+
+### 5. Aggregate Priority Actions
+
+```javascript
+const allPriorityActions = domains.flatMap((domain) =>
+  assessments[domain].priority_actions.map((action) => ({
+    domain,
+    action,
+    urgency: assessments[domain].risk_level === 'HIGH' ? 'URGENT' : 'NORMAL',
+  })),
+);
+
+// Sort by urgency
+const prioritizedActions = allPriorityActions.sort((a, b) => (a.urgency === 'URGENT' ? -1 : 1));
+```
+
+---
+
+### 6. Generate Executive Summary
+
+```javascript
+const resolvedMode = subagentContext?.execution?.resolvedMode ?? 'unknown';
+const subagentExecutionLabel =
+  resolvedMode === 'sequential'
+    ? 'SEQUENTIAL (4 NFR domains)'
+    : resolvedMode === 'agent-team'
+      ? 'AGENT-TEAM (4 NFR domains)'
+      : resolvedMode === 'subagent'
+        ? 'SUBAGENT (4 NFR domains)'
+        : 'MODE-DEPENDENT (4 NFR domains)';
+
+const performanceGainLabel =
+  resolvedMode === 'sequential'
+    ? 'baseline (no parallel speedup)'
+    : resolvedMode === 'agent-team' || resolvedMode === 'subagent'
+      ? '~67% faster than sequential'
+      : 'mode-dependent';
+
+const executiveSummary = {
+  overall_risk: overallRisk,
+  assessment_date: new Date().toISOString(),
+
+  domain_assessments: assessments,
+
+  compliance_summary: complianceSummary,
+
+  cross_domain_risks: crossDomainRisks,
+
+  priority_actions: prioritizedActions,
+
+  risk_breakdown: {
+    security: assessments.security.risk_level,
+    performance: assessments.performance.risk_level,
+    reliability: assessments.reliability.risk_level,
+    scalability: assessments.scalability.risk_level,
+  },
+
+  subagent_execution: subagentExecutionLabel,
+  performance_gain: performanceGainLabel,
+};
+
+// Save for Step 5 (report generation)
+fs.writeFileSync('/tmp/tea-nfr-summary-{{timestamp}}.json', JSON.stringify(executiveSummary, null, 2), 'utf8');
+```
+
+---
+
+### 7. Display Summary to User
+
+```
+✅ NFR Assessment Complete ({subagentExecutionLabel})
+
+🎯 Overall Risk Level: {overallRisk}
+
+📊 Domain Risk Breakdown:
+- Security:      {security_risk}
+- Performance:   {performance_risk}
+- Reliability:   {reliability_risk}
+- Scalability:   {scalability_risk}
+
+✅ Compliance Summary:
+{list standards with PASS/PARTIAL/FAIL}
+
+⚠️ Cross-Domain Risks: {cross_domain_risk_count}
+
+🎯 Priority Actions: {priority_action_count}
+
+🚀 Performance: {performanceGainLabel}
+
+✅ Ready for report generation (Step 5)
+```
+
+---
+
+---
+
+### 8. Save Progress
+
+**Save this step's accumulated work to `{outputFile}`.**
+
+- **If `{outputFile}` does not exist** (first save), create it using the workflow template (if available) with YAML frontmatter:
+
+  ```yaml
+  ---
+  stepsCompleted: ['step-04e-aggregate-nfr']
+  lastStep: 'step-04e-aggregate-nfr'
+  lastSaved: '{date}'
+  ---
+  ```
+
+  Then write this step's output below the frontmatter.
+
+- **If `{outputFile}` already exists**, update:
+  - Add `'step-04e-aggregate-nfr'` to `stepsCompleted` array (only if not already present)
+  - Set `lastStep: 'step-04e-aggregate-nfr'`
+  - Set `lastSaved: '{date}'`
+  - Append this step's output to the appropriate section of the document.
+
+---
+
+## EXIT CONDITION
+
+Proceed to Step 5 when:
+
+- ✅ All subagent outputs read
+- ✅ Overall risk calculated
+- ✅ Compliance aggregated
+- ✅ Summary saved
+- ✅ Progress saved to output document
+
+Load next step: `{nextStepFile}`
+
+---
+
+## 🚨 SYSTEM SUCCESS METRICS
+
+### ✅ SUCCESS:
+
+- All 4 NFR domains aggregated correctly
+- Overall risk level determined
+- Executive summary complete
+
+### ❌ FAILURE:
+
+- Failed to read subagent outputs
+- Risk calculation incorrect

package/lib/bmad-cache/tea/src/workflows/testarch/bmad-testarch-nfr/steps-c/step-05-generate-report.md

@@ -0,0 +1,108 @@
+---
+name: 'step-05-generate-report'
+description: 'Create NFR report and validation summary'
+outputFile: '{test_artifacts}/nfr-assessment.md'
+---
+
+# Step 5: Generate Report & Validate
+
+## STEP GOAL
+
+Produce the NFR assessment report and validate completeness.
+
+## MANDATORY EXECUTION RULES
+
+- 📖 Read the entire step file before acting
+- ✅ Speak in `{communication_language}`
+
+---
+
+## EXECUTION PROTOCOLS:
+
+- 🎯 Follow the MANDATORY SEQUENCE exactly
+- 💾 Record outputs before proceeding
+- 📖 Load the next step only when instructed
+
+## CONTEXT BOUNDARIES:
+
+- Available context: config, loaded artifacts, and knowledge fragments
+- Focus: this step's goal only
+- Limits: do not execute future steps
+- Dependencies: prior steps' outputs (if any)
+
+## MANDATORY SEQUENCE
+
+**CRITICAL:** Follow this sequence exactly. Do not skip, reorder, or improvise.
+
+## 1. Report Generation
+
+Use `nfr-report-template.md` to produce `{outputFile}` containing:
+
+- Category results (PASS/CONCERNS/FAIL)
+- Evidence summary
+- Remediation actions
+- Gate-ready YAML snippet (if applicable)
+
+---
+
+## 2. Polish Output
+
+Before finalizing, review the complete output document for quality:
+
+1. **Remove duplication**: Progressive-append workflow may have created repeated sections — consolidate
+2. **Verify consistency**: Ensure terminology, risk scores, and references are consistent throughout
+3. **Check completeness**: All template sections should be populated or explicitly marked N/A
+4. **Format cleanup**: Ensure markdown formatting is clean (tables aligned, headers consistent, no orphaned references)
+
+---
+
+## 3. Validation
+
+Validate against `checklist.md` and fix gaps.
+
+- [ ] CLI sessions cleaned up (no orphaned browsers)
+
+---
+
+## 4. Save Progress
+
+**Save this step's accumulated work to `{outputFile}`.**
+
+- **If `{outputFile}` does not exist** (first save), create it using the workflow template (if available) with YAML frontmatter:
+
+  ```yaml
+  ---
+  stepsCompleted: ['step-05-generate-report']
+  lastStep: 'step-05-generate-report'
+  lastSaved: '{date}'
+  ---
+  ```
+
+  Then write this step's output below the frontmatter.
+
+- **If `{outputFile}` already exists**, update:
+  - Add `'step-05-generate-report'` to `stepsCompleted` array (only if not already present)
+  - Set `lastStep: 'step-05-generate-report'`
+  - Set `lastSaved: '{date}'`
+  - Append this step's output to the appropriate section of the document.
+
+---
+
+## 5. Completion Summary
+
+Report:
+
+- Overall NFR status
+- Critical blockers or waivers needed
+- Next recommended workflow (`trace` or release gate)
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS:
+
+### ✅ SUCCESS:
+
+- Step completed in full with required outputs
+
+### ❌ SYSTEM FAILURE:
+
+- Skipped sequence steps or missing outputs
+  **Master Rule:** Skipping steps is FORBIDDEN.

package/lib/bmad-cache/tea/src/workflows/testarch/bmad-testarch-nfr/steps-e/step-01-assess.md

@@ -0,0 +1,65 @@
+---
+name: 'step-01-assess'
+description: 'Load an existing output for editing'
+nextStepFile: './step-02-apply-edit.md'
+---
+
+# Step 1: Assess Edit Target
+
+## STEP GOAL:
+
+Identify which output should be edited and load it.
+
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+### Universal Rules:
+
+- 📖 Read the complete step file before taking any action
+- ✅ Speak in `{communication_language}`
+
+### Role Reinforcement:
+
+- ✅ You are the Master Test Architect
+
+### Step-Specific Rules:
+
+- 🎯 Ask the user which output file to edit
+- 🚫 Do not edit until target is confirmed
+
+## EXECUTION PROTOCOLS:
+
+- 🎯 Follow the MANDATORY SEQUENCE exactly
+
+## CONTEXT BOUNDARIES:
+
+- Available context: existing outputs
+- Focus: select edit target
+- Limits: no edits yet
+
+## MANDATORY SEQUENCE
+
+**CRITICAL:** Follow this sequence exactly.
+
+### 1. Identify Target
+
+Ask the user to provide the output file path or select from known outputs.
+
+### 2. Load Target
+
+Read the provided output file in full.
+
+### 3. Confirm
+
+Confirm the target and proceed to edit.
+
+Load next step: `{nextStepFile}`
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS:
+
+### ✅ SUCCESS:
+
+- Target identified and loaded
+
+### ❌ SYSTEM FAILURE:
+
+- Proceeding without a confirmed target

package/lib/bmad-cache/tea/src/workflows/testarch/bmad-testarch-nfr/steps-e/step-02-apply-edit.md

@@ -0,0 +1,60 @@
+---
+name: 'step-02-apply-edit'
+description: 'Apply edits to the selected output'
+---
+
+# Step 2: Apply Edits
+
+## STEP GOAL:
+
+Apply the requested edits to the selected output and confirm changes.
+
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+### Universal Rules:
+
+- 📖 Read the complete step file before taking any action
+- ✅ Speak in `{communication_language}`
+
+### Role Reinforcement:
+
+- ✅ You are the Master Test Architect
+
+### Step-Specific Rules:
+
+- 🎯 Only apply edits explicitly requested by the user
+
+## EXECUTION PROTOCOLS:
+
+- 🎯 Follow the MANDATORY SEQUENCE exactly
+
+## CONTEXT BOUNDARIES:
+
+- Available context: selected output and user changes
+- Focus: apply edits only
+
+## MANDATORY SEQUENCE
+
+**CRITICAL:** Follow this sequence exactly.
+
+### 1. Confirm Requested Changes
+
+Restate what will be changed and confirm.
+
+### 2. Apply Changes
+
+Update the output file accordingly.
+
+### 3. Report
+
+Summarize the edits applied.
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS:
+
+### ✅ SUCCESS:
+
+- Changes applied and confirmed
+
+### ❌ SYSTEM FAILURE:
+
+- Unconfirmed edits or missing update