@stackmemoryai/stackmemory 0.3.17 → 0.3.18

package/scripts/test-rlm-comprehensive.sh

@@ -0,0 +1,260 @@
+#!/bin/bash
+
+# Comprehensive RLM End-to-End Test
+echo "============================================"
+echo "Comprehensive RLM End-to-End Test"
+echo "Testing all RLM orchestrator capabilities"
+echo "============================================"
+echo ""
+
+# Colors for output
+GREEN='\033[0;32m'
+RED='\033[0;31m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m'
+
+# Results tracking
+TOTAL_TESTS=0
+PASSED_TESTS=0
+FAILED_TESTS=0
+
+# Test function
+test_rlm() {
+    local test_name="$1"
+    local test_input="$2"
+    local check_for="$3"
+    
+    echo -e "${BLUE}Testing: $test_name${NC}"
+    TOTAL_TESTS=$((TOTAL_TESTS + 1))
+    
+    OUTPUT=$(stackmemory skills rlm "$test_input" 2>&1)
+    
+    if echo "$OUTPUT" | grep -q "$check_for"; then
+        echo -e "${GREEN}  ✓ PASSED: Found '$check_for'${NC}"
+        PASSED_TESTS=$((PASSED_TESTS + 1))
+        return 0
+    else
+        echo -e "${RED}  ✗ FAILED: Did not find '$check_for'${NC}"
+        FAILED_TESTS=$((FAILED_TESTS + 1))
+        return 1
+    fi
+}
+
+# Build the project
+echo "Building project..."
+npm run build > /dev/null 2>&1
+
+echo ""
+echo "Running comprehensive tests..."
+echo "------------------------------"
+echo ""
+
+# Test 1: Basic execution
+echo "1. Basic RLM Execution Tests"
+echo "=============================="
+test_rlm "Execution completion" "Write a simple function" "RLM execution completed"
+test_rlm "Frame creation" "Create hello world" "Created frame"
+test_rlm "Frame closure" "Simple task" "Closed frame"
+test_rlm "Planning phase" "Design a feature" "planning subagent"
+test_rlm "Review phase" "Review this code" "Review stage.*complete"
+test_rlm "Quality check" "Optimize performance" "Quality threshold met"
+
+echo ""
+echo "2. Subagent Orchestration Tests"
+echo "================================="
+test_rlm "Planning agent" "Plan a complex feature" "Spawning planning subagent"
+test_rlm "Review agent" "Review and improve code" "Spawning review subagent"
+test_rlm "Mock response handling" "Generate tests" "Review stage 1 complete"
+
+echo ""
+echo "3. Multi-Stage Review Tests"
+echo "============================="
+OUTPUT=$(stackmemory skills rlm "Complex refactoring task" 2>&1)
+echo "$OUTPUT" | grep -E "Review stage [0-9]" | while read -r line; do
+    echo -e "${GREEN}  ✓ Found: $line${NC}"
+done
+
+echo ""
+echo "4. Execution Metrics Tests"
+echo "============================"
+OUTPUT=$(stackmemory skills rlm "Create API endpoint" 2>&1)
+echo -e "${BLUE}Checking metrics...${NC}"
+
+if echo "$OUTPUT" | grep -q "Total tokens:"; then
+    echo -e "${GREEN}  ✓ Token tracking present${NC}"
+    PASSED_TESTS=$((PASSED_TESTS + 1))
+else
+    echo -e "${RED}  ✗ Token tracking missing${NC}"
+    FAILED_TESTS=$((FAILED_TESTS + 1))
+fi
+TOTAL_TESTS=$((TOTAL_TESTS + 1))
+
+if echo "$OUTPUT" | grep -q "Estimated cost:"; then
+    echo -e "${GREEN}  ✓ Cost estimation present${NC}"
+    PASSED_TESTS=$((PASSED_TESTS + 1))
+else
+    echo -e "${RED}  ✗ Cost estimation missing${NC}"
+    FAILED_TESTS=$((FAILED_TESTS + 1))
+fi
+TOTAL_TESTS=$((TOTAL_TESTS + 1))
+
+if echo "$OUTPUT" | grep -q "Duration:"; then
+    echo -e "${GREEN}  ✓ Duration tracking present${NC}"
+    PASSED_TESTS=$((PASSED_TESTS + 1))
+else
+    echo -e "${RED}  ✗ Duration tracking missing${NC}"
+    FAILED_TESTS=$((FAILED_TESTS + 1))
+fi
+TOTAL_TESTS=$((TOTAL_TESTS + 1))
+
+echo ""
+echo "5. Error Recovery Tests"
+echo "========================"
+test_rlm "Empty input handling" "" "RLM execution"
+test_rlm "Retry mechanism" "Task with retries" "Retrying node"
+
+echo ""
+echo "6. Complex Feature Tests"
+echo "========================="
+# Test with a complex multi-line feature request
+COMPLEX_FEATURE=$(cat <<'EOF'
+Create a complete user authentication system with:
+- JWT token generation
+- Password hashing with bcrypt
+- Email verification
+- Rate limiting
+- Session management
+- OAuth integration
+EOF
+)
+
+OUTPUT=$(stackmemory skills rlm "$COMPLEX_FEATURE" 2>&1)
+if echo "$OUTPUT" | grep -q "RLM execution completed"; then
+    echo -e "${GREEN}  ✓ Complex feature handled${NC}"
+    PASSED_TESTS=$((PASSED_TESTS + 1))
+else
+    echo -e "${RED}  ✗ Complex feature failed${NC}"
+    FAILED_TESTS=$((FAILED_TESTS + 1))
+fi
+TOTAL_TESTS=$((TOTAL_TESTS + 1))
+
+echo ""
+echo "7. Improvements & Suggestions Tests"
+echo "====================================="
+OUTPUT=$(stackmemory skills rlm "Improve this function" 2>&1)
+if echo "$OUTPUT" | grep -q "Improvements:"; then
+    echo -e "${GREEN}  ✓ Improvements generated${NC}"
+    echo "  Improvements found:"
+    echo "$OUTPUT" | grep -A 3 "Improvements:" | tail -3 | sed 's/^/    /'
+    PASSED_TESTS=$((PASSED_TESTS + 1))
+else
+    echo -e "${RED}  ✗ No improvements generated${NC}"
+    FAILED_TESTS=$((FAILED_TESTS + 1))
+fi
+TOTAL_TESTS=$((TOTAL_TESTS + 1))
+
+echo ""
+echo "8. Database Persistence Tests"
+echo "=============================="
+echo -e "${BLUE}Checking database operations...${NC}"
+
+# Get initial frame count
+INITIAL_STATUS=$(stackmemory status 2>&1)
+INITIAL_FRAMES=$(echo "$INITIAL_STATUS" | grep -oE "Frames: [0-9]+" | awk '{print $2}' || echo "0")
+
+# Execute a task
+stackmemory skills rlm "Test task for persistence" > /dev/null 2>&1
+
+# Get new frame count
+FINAL_STATUS=$(stackmemory status 2>&1)
+FINAL_FRAMES=$(echo "$FINAL_STATUS" | grep -oE "Frames: [0-9]+" | awk '{print $2}' || echo "0")
+
+echo "  Initial frames: ${INITIAL_FRAMES:-0}"
+echo "  Final frames: ${FINAL_FRAMES:-0}"
+
+if [ "${FINAL_FRAMES:-0}" -ge "${INITIAL_FRAMES:-0}" ]; then
+    echo -e "${GREEN}  ✓ Database operations working${NC}"
+    PASSED_TESTS=$((PASSED_TESTS + 1))
+else
+    echo -e "${YELLOW}  ⚠ Frame count decreased (cleanup may have occurred)${NC}"
+fi
+TOTAL_TESTS=$((TOTAL_TESTS + 1))
+
+echo ""
+echo "9. Performance Tests"
+echo "===================="
+echo -e "${BLUE}Testing execution speed...${NC}"
+
+START_TIME=$(date +%s%N)
+stackmemory skills rlm "Quick task" > /dev/null 2>&1
+END_TIME=$(date +%s%N)
+DURATION=$(( (END_TIME - START_TIME) / 1000000 ))
+
+echo "  Execution time: ${DURATION}ms"
+
+if [ "$DURATION" -lt 5000 ]; then
+    echo -e "${GREEN}  ✓ Fast execution (< 5 seconds)${NC}"
+    PASSED_TESTS=$((PASSED_TESTS + 1))
+else
+    echo -e "${YELLOW}  ⚠ Slow execution (> 5 seconds)${NC}"
+fi
+TOTAL_TESTS=$((TOTAL_TESTS + 1))
+
+echo ""
+echo "10. Integration Tests"
+echo "====================="
+echo -e "${BLUE}Testing full workflow...${NC}"
+
+# Create a test file with multiple requirements
+cat > /tmp/full-test.md << 'EOF'
+# Complete Feature Implementation
+Build a REST API with the following:
+1. User CRUD operations
+2. Authentication middleware
+3. Input validation
+4. Error handling
+5. Unit tests
+6. API documentation
+EOF
+
+OUTPUT=$(stackmemory skills rlm "$(cat /tmp/full-test.md)" 2>&1)
+
+# Check for all major components
+COMPONENTS=("planning" "review" "Quality" "Improvements" "RLM execution completed")
+for component in "${COMPONENTS[@]}"; do
+    TOTAL_TESTS=$((TOTAL_TESTS + 1))
+    if echo "$OUTPUT" | grep -q "$component"; then
+        echo -e "${GREEN}  ✓ $component found${NC}"
+        PASSED_TESTS=$((PASSED_TESTS + 1))
+    else
+        echo -e "${RED}  ✗ $component missing${NC}"
+        FAILED_TESTS=$((FAILED_TESTS + 1))
+    fi
+done
+
+# Clean up
+rm -f /tmp/full-test.md
+
+echo ""
+echo "============================================"
+echo "Test Summary"
+echo "============================================"
+echo -e "Total tests run: ${TOTAL_TESTS}"
+echo -e "${GREEN}Tests passed: ${PASSED_TESTS}${NC}"
+echo -e "${RED}Tests failed: ${FAILED_TESTS}${NC}"
+
+SUCCESS_RATE=$(( (PASSED_TESTS * 100) / TOTAL_TESTS ))
+echo -e "Success rate: ${SUCCESS_RATE}%"
+
+echo ""
+if [ "$FAILED_TESTS" -eq 0 ]; then
+    echo -e "${GREEN}✨ All tests passed! RLM system is fully operational.${NC}"
+    exit 0
+elif [ "$SUCCESS_RATE" -ge 80 ]; then
+    echo -e "${YELLOW}⚠️  Most tests passed (${SUCCESS_RATE}%). System is mostly operational.${NC}"
+    exit 0
+else
+    echo -e "${RED}❌ Too many failures (${SUCCESS_RATE}% success). System needs attention.${NC}"
+    exit 1
+fi

package/scripts/test-rlm-e2e.sh

@@ -0,0 +1,268 @@
+#!/bin/bash
+
+# StackMemory RLM End-to-End Test Script
+# Tests all aspects of the RLM orchestrator system
+
+set -e
+
+echo "========================================="
+echo "StackMemory RLM End-to-End Test Suite"
+echo "========================================="
+echo ""
+
+# Colors for output
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+NC='\033[0m' # No Color
+
+# Test counter
+TESTS_PASSED=0
+TESTS_FAILED=0
+
+# Function to run a test
+run_test() {
+    local test_name="$1"
+    local test_command="$2"
+    
+    echo -e "${YELLOW}Running test: $test_name${NC}"
+    
+    if eval "$test_command" > /tmp/rlm-test-output.txt 2>&1; then
+        echo -e "${GREEN}✓ PASSED: $test_name${NC}"
+        ((TESTS_PASSED++))
+        return 0
+    else
+        echo -e "${RED}✗ FAILED: $test_name${NC}"
+        echo "Error output:"
+        tail -n 20 /tmp/rlm-test-output.txt
+        ((TESTS_FAILED++))
+        return 1
+    fi
+}
+
+# Function to check output contains string
+check_output() {
+    local search_string="$1"
+    if grep -q "$search_string" /tmp/rlm-test-output.txt; then
+        return 0
+    else
+        echo "Expected output not found: $search_string"
+        return 1
+    fi
+}
+
+# Build the project first
+echo "Building project..."
+npm run build > /dev/null 2>&1
+
+echo ""
+echo "Starting RLM tests..."
+echo ""
+
+# Test 1: Simple feature request
+echo "Test 1: Simple Feature Implementation"
+cat > /tmp/test-simple.md << 'EOF'
+# Simple Calculator Function
+Create a function that adds two numbers together.
+Requirements:
+- Function name: addNumbers
+- Takes two parameters: a and b
+- Returns the sum
+- Include type checking
+EOF
+
+run_test "Simple feature execution" "stackmemory skills rlm \"\$(cat /tmp/test-simple.md)\" 2>&1"
+if [ $? -eq 0 ]; then
+    run_test "Simple feature completion" "check_output 'RLM execution completed'"
+    run_test "Simple feature frames" "check_output 'Created frame'"
+    run_test "Simple feature planning" "check_output 'planning subagent'"
+    run_test "Simple feature review" "check_output 'Review stage.*complete'"
+fi
+
+# Test 2: Complex API feature
+echo ""
+echo "Test 2: Complex API Implementation"
+cat > /tmp/test-api.md << 'EOF'
+# REST API for Task Management
+Create a complete REST API for task management:
+- GET /tasks - List all tasks with pagination
+- GET /tasks/:id - Get single task
+- POST /tasks - Create task with validation
+- PUT /tasks/:id - Update task
+- DELETE /tasks/:id - Soft delete task
+Requirements:
+- Express.js with TypeScript
+- Input validation using Joi or Zod
+- Error handling middleware
+- Unit tests with Jest
+- API documentation
+EOF
+
+run_test "Complex API execution" "stackmemory skills rlm \"\$(cat /tmp/test-api.md)\""
+if [ $? -eq 0 ]; then
+    run_test "Complex API planning phase" "check_output 'Spawning planning subagent'"
+    run_test "Complex API review stage" "check_output 'Review stage.*complete'"
+fi
+
+# Test 3: Refactoring request
+echo ""
+echo "Test 3: Code Refactoring"
+cat > /tmp/test-refactor.md << 'EOF'
+# Refactor Legacy Code
+Refactor the following patterns:
+- Convert callbacks to async/await
+- Extract common logic into utilities
+- Add proper error handling
+- Improve variable naming
+- Add TypeScript types
+EOF
+
+run_test "Refactoring execution" "stackmemory skills rlm \"\$(cat /tmp/test-refactor.md)\""
+
+# Test 4: Test generation
+echo ""
+echo "Test 4: Test Generation"
+cat > /tmp/test-generate.md << 'EOF'
+# Generate Comprehensive Test Suite
+Create tests for a user authentication module:
+- Unit tests for validation logic
+- Integration tests for API endpoints
+- Mock external services
+- Test error scenarios
+- Achieve 90% coverage
+EOF
+
+run_test "Test generation execution" "stackmemory skills rlm \"\$(cat /tmp/test-generate.md)\""
+if [ $? -eq 0 ]; then
+    run_test "Test generation quality check" "check_output 'Quality threshold met'"
+fi
+
+# Test 5: Documentation task
+echo ""
+echo "Test 5: Documentation Generation"
+cat > /tmp/test-docs.md << 'EOF'
+# API Documentation
+Generate comprehensive documentation:
+- API endpoint descriptions
+- Request/response examples
+- Authentication details
+- Error codes
+- Usage examples
+EOF
+
+run_test "Documentation execution" "stackmemory skills rlm \"\$(cat /tmp/test-docs.md)\""
+
+# Test 6: Performance optimization
+echo ""
+echo "Test 6: Performance Optimization"
+cat > /tmp/test-perf.md << 'EOF'
+# Optimize Database Queries
+Improve performance:
+- Add appropriate indexes
+- Optimize N+1 queries
+- Implement caching layer
+- Add query pagination
+- Profile slow queries
+EOF
+
+run_test "Performance optimization execution" "stackmemory skills rlm \"\$(cat /tmp/test-perf.md)\""
+
+# Test 7: Security review
+echo ""
+echo "Test 7: Security Review"
+cat > /tmp/test-security.md << 'EOF'
+# Security Audit
+Review and fix security issues:
+- SQL injection prevention
+- XSS protection
+- CSRF tokens
+- Input sanitization
+- Authentication checks
+EOF
+
+run_test "Security review execution" "stackmemory skills rlm \"\$(cat /tmp/test-security.md)\""
+
+# Test 8: Database persistence
+echo ""
+echo "Test 8: Database Frame Persistence"
+run_test "Check frame persistence" "stackmemory status | grep -E 'Frames: [0-9]+'"
+
+# Test 9: Parallel execution test
+echo ""
+echo "Test 9: Parallel Task Execution"
+cat > /tmp/test-parallel.md << 'EOF'
+# Multiple Independent Tasks
+Execute these tasks in parallel:
+1. Generate user model
+2. Create API routes
+3. Write test cases
+4. Setup database schema
+5. Create documentation
+EOF
+
+run_test "Parallel execution" "stackmemory skills rlm \"\$(cat /tmp/test-parallel.md)\""
+
+# Test 10: Error recovery
+echo ""
+echo "Test 10: Error Recovery"
+cat > /tmp/test-error.md << 'EOF'
+# Handle Errors Gracefully
+This has some problematic requirements:
+- Use undefined library XYZ123
+- Connect to non-existent service
+- Still produce meaningful output
+EOF
+
+run_test "Error recovery execution" "stackmemory skills rlm \"\$(cat /tmp/test-error.md)\""
+
+# Test 11: Quality threshold testing
+echo ""
+echo "Test 11: Quality Threshold"
+run_test "Quality threshold check" "stackmemory skills rlm \"Write a hello world function\" | grep -E 'Quality threshold met: .* >= 0.85'"
+
+# Test 12: Token and cost tracking
+echo ""
+echo "Test 12: Metrics Tracking"
+run_test "Token tracking" "stackmemory skills rlm \"Create a simple function\" | grep -E 'Total tokens:'"
+run_test "Cost estimation" "stackmemory skills rlm \"Create a simple function\" | grep -E 'Estimated cost:'"
+
+# Test 13: Subagent types
+echo ""
+echo "Test 13: All Subagent Types"
+for agent in "planning" "code" "testing" "linting" "review" "improve" "context"; do
+    run_test "Subagent $agent" "stackmemory skills rlm \"Task requiring $agent\" | grep -i \"$agent\""
+done
+
+# Test 14: Frame lifecycle
+echo ""
+echo "Test 14: Frame Lifecycle"
+OUTPUT=$(stackmemory skills rlm "Quick task" 2>&1)
+echo "$OUTPUT" > /tmp/rlm-test-output.txt
+run_test "Frame created" "check_output 'Created frame'"
+run_test "Frame closed" "check_output 'Closed frame'"
+
+# Test 15: Mock mode verification
+echo ""
+echo "Test 15: Mock Mode Active"
+run_test "Mock mode enabled" "stackmemory skills rlm \"Test task\" | grep -E 'mockMode: true|Mock .* subagent completed successfully'"
+
+# Clean up test files
+rm -f /tmp/test-*.md
+rm -f /tmp/rlm-test-output.txt
+
+# Summary
+echo ""
+echo "========================================="
+echo "Test Results Summary"
+echo "========================================="
+echo -e "${GREEN}Tests Passed: $TESTS_PASSED${NC}"
+echo -e "${RED}Tests Failed: $TESTS_FAILED${NC}"
+echo ""
+
+if [ $TESTS_FAILED -eq 0 ]; then
+    echo -e "${GREEN}✓ All tests passed successfully!${NC}"
+    exit 0
+else
+    echo -e "${RED}✗ Some tests failed. Please review the output above.${NC}"
+    exit 1
+fi

package/scripts/test-rlm-simple.js

@@ -0,0 +1,90 @@
+#!/usr/bin/env node
+
+import 'dotenv/config';
+import { ClaudeCodeSubagentClient } from '../dist/integrations/claude-code/subagent-client.js';
+
+async function testRLMSimple() {
+  console.log('🚀 Testing RLM Subagent Client (Simple Mode)...\n');
+  
+  try {
+    // Initialize the subagent client
+    console.log('🤖 Creating Subagent Client...');
+    const client = new ClaudeCodeSubagentClient();
+    
+    // Test with different subagent types
+    const testCases = [
+      {
+        type: 'planning',
+        task: 'Create a simple hello world function',
+        context: { language: 'JavaScript', style: 'functional' }
+      },
+      {
+        type: 'code',
+        task: 'Implement a hello world function in JavaScript',
+        context: { requirements: 'Should return "Hello, World!"' }
+      },
+      {
+        type: 'testing',
+        task: 'Generate tests for a hello world function',
+        context: { code: 'function hello() { return "Hello, World!"; }' }
+      }
+    ];
+    
+    for (const testCase of testCases) {
+      console.log(`\n📝 Testing ${testCase.type} subagent:`);
+      console.log(`   Task: "${testCase.task}"`);
+      
+      // Use mock mode for testing
+      const result = await client.mockTaskToolExecution({
+        type: testCase.type,
+        task: testCase.task,
+        context: testCase.context
+      });
+      
+      if (result.success) {
+        console.log(`   ✅ Success!`);
+        console.log(`   ⏱️  Duration: ${result.duration}ms`);
+        console.log(`   📊 Tokens: ~${result.tokens || 'N/A'}`);
+        
+        if (testCase.type === 'planning' && result.result?.tasks) {
+          console.log(`   📋 Generated ${result.result.tasks.length} subtasks`);
+        } else if (testCase.type === 'code' && result.result?.implementation) {
+          console.log(`   💻 Generated code (${result.result.implementation.length} chars)`);
+        } else if (testCase.type === 'testing' && result.result?.tests) {
+          console.log(`   🧪 Generated ${result.result.tests.length} test cases`);
+        }
+      } else {
+        console.log(`   ❌ Failed: ${result.error}`);
+      }
+    }
+    
+    console.log('\n\n🎯 Testing Parallel Execution:');
+    const parallelRequests = [
+      { type: 'code', task: 'Create add function', context: {} },
+      { type: 'code', task: 'Create subtract function', context: {} },
+      { type: 'testing', task: 'Test math functions', context: {} }
+    ];
+    
+    console.log(`   Executing ${parallelRequests.length} subagents in parallel...`);
+    const startTime = Date.now();
+    
+    const results = await client.executeParallel(
+      parallelRequests.map(req => ({ ...req, type: req.type }))
+    );
+    
+    const duration = Date.now() - startTime;
+    const successful = results.filter(r => r.success).length;
+    
+    console.log(`   ⏱️  Completed in ${duration}ms`);
+    console.log(`   ✅ ${successful}/${results.length} successful`);
+    
+    console.log('\n✨ Test complete!');
+    
+  } catch (error) {
+    console.error('💥 Test failed:', error);
+    process.exit(1);
+  }
+}
+
+// Run the test
+testRLMSimple().catch(console.error);