How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

tests - Prompt - OpenSmartRoute

Name: tests
Author: danilonovaisv

Prompt file imported from danilonovaisv/PROMPT-APP (.windsurf/workflows/tests.md). Copyright stays with the author.

/tests - Comprehensive Testing System

Manage, run, and analyze all tests across the MAx Framework with comprehensive reporting and debugging capabilities.

Usage

# Run all tests with comprehensive reporting
/tests

# Run specific test category
/tests --category unit
/tests --category integration
/tests --category system

# Run tests with specific focus
/tests --focus contracts
/tests --focus commands
/tests --focus quality

# Run tests with detailed output
/tests --verbose

# Run tests with auto-fix enabled
/tests --auto-fix

# Generate test report
/tests --report

# Quick test run
/tests --quick

Test Categories

🧪 Unit Tests

Individual component testing
Function and method validation
Class and module testing
Edge case coverage

🔗 Integration Tests

Component interaction testing
Cross-module functionality
API integration validation
Workflow testing

🏗️ System Tests

End-to-end workflows
Framework integration
Performance validation
User scenario testing

📋 Contract Tests

AI contract validation
Code quality standards
Performance contracts
Security contracts

Test Focus Areas

🎯 Contracts Focus

/tests --focus contracts

AI contract compliance
Code quality standards
Performance benchmarks
Security validations

⚡ Commands Focus

/tests --focus commands

Command execution testing
Argument parsing validation
Error handling verification
Integration testing

🔍 Quality Focus

/tests --focus quality

Code quality metrics
Style guide compliance
Documentation coverage
Best practices validation

Test Execution Options

📊 Comprehensive Mode

/tests

All test categories
Detailed reporting
Performance metrics
Coverage analysis
Error categorization

⚡ Quick Mode

/tests --quick

Essential tests only
Minimal output
Fast execution
Basic reporting

🔧 Auto-Fix Mode

/tests --auto-fix

Automatic error fixing
Import resolution
Syntax correction
Missing method addition

📋 Report Mode

/tests --report

Detailed test report
Coverage statistics
Performance analysis
Trend tracking

Test Discovery

🔍 Test File Patterns

test_*.py - Unit test files
*_test.py - Alternative test naming
tests/**/*.py - Test directory structure
**/test_*.py - Recursive discovery

📁 Test Directory Structure

tests/
├── unit/                    # Unit tests
│   ├── test_commands.py
│   ├── test_quality.py
│   └── test_contracts.py
├── integration/             # Integration tests
│   ├── test_workflows.py
│   ├── test_systems.py
│   └── test_apis.py
├── system/                  # System tests
│   ├── test_end_to_end.py
│   ├── test_performance.py
│   └── test_user_scenarios.py
└── reports/                 # Test reports
    ├── coverage.json
    ├── results.json
    └── trends.json

Test Results

📊 Success Metrics

✅ PASSED: 42 tests (85%)
⚠️ SKIPPED: 5 tests (10%)
❌ FAILED: 3 tests (5%)
⏱️ Duration: 2.34s
📊 Coverage: 87.3%

🚨 Failure Analysis

❌ FAILED TESTS:
1. test_command_execution
   - Error: AssertionError
   - Location: tests/commands/test_commands.py:42
   - Message: Expected success but got error

2. test_contract_validation
   - Error: ImportError
   - Location: tests/contracts/test_ai.py:15
   - Message: Missing required import

3. test_quality_metrics
   - Error: TimeoutError
   - Location: tests/quality/test_metrics.py:78
   - Message: Test exceeded 30s timeout

🔧 Auto-Fix Results

🔧 APPLIED FIXES:
1. Added missing import: import unittest
2. Fixed syntax error: print statement
3. Added missing method: setUp()
4. Corrected indentation: 4 spaces

Configuration

⚙️ Test Configuration

{
  "test_paths": ["tests/", "test_*.py", "*_test.py"],
  "test_categories": ["unit", "integration", "system", "contracts"],
  "timeout": 30,
  "auto_fix": true,
  "verbose": true,
  "coverage": true,
  "parallel": true
}

🎯 Environment Variables

# Enable auto-fix
export MAX_TESTS_AUTO_FIX=1

# Set test timeout
export MAX_TESTS_TIMEOUT=60

# Enable verbose output
export MAX_TESTS_VERBOSE=1

# Disable parallel execution
export MAX_TESTS_SEQUENTIAL=1

Integration

🔄 CI/CD Integration

# .github/workflows/tests.yml
name: Comprehensive Tests
on: [push, pull_request]
jobs:
  test:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v2
      - name: Run comprehensive tests
        run: /tests --report
      - name: Upload test results
        uses: actions/upload-artifact@v2
        with:
          name: test-results
          path: tests/reports/

🔧 Pre-commit Hook

#!/bin/sh
# .git/hooks/pre-commit
/tests --quick
if [ $? -ne 0 ]; then
    echo "❌ Tests failed - commit blocked"
    exit 1
fi

📊 Quality Gate Integration

# Run as part of quality gate
/max-quality --include-tests

# Fail build on test failures
/tests --strict

Advanced Features

🎯 Test Filtering

# Run tests matching pattern
/tests --pattern "test_*contract*"

# Exclude specific tests
/tests --exclude "test_slow_*"

# Run tests by file
/tests --file test_commands.py

# Run tests by directory
/tests --directory tests/unit/

📈 Performance Testing

# Run performance benchmarks
/tests --performance

# Measure execution time
/tests --timing

# Memory usage analysis
/tests --memory

🔍 Debug Mode

# Run with debugger
/tests --debug

# Stop on first failure
/tests --failfast

# Run with detailed tracebacks
/tests --traceback

Reports

📊 Coverage Report

/tests --coverage

Line coverage: 87.3%
Branch coverage: 82.1%
Function coverage: 91.5%
Missing coverage: 12.7%

📈 Trend Analysis

/tests --trends

Test count trend: +5 tests this week
Success rate trend: 92% → 95%
Performance trend: -0.2s average
Coverage trend: +2.3% this month

📋 Detailed Report

/tests --report --detailed

Test execution summary
Failure analysis
Performance metrics
Coverage breakdown
Recommendations

Benefits

🎯 Comprehensive Coverage

All test types: Unit, integration, system, contracts
Multiple frameworks: unittest, pytest, custom
Cross-platform: Linux, macOS, Windows
Language support: Python, JavaScript, Shell

🔧 Intelligent Testing

Auto-fix capabilities: Common error resolution
Smart discovery: Automatic test finding
Parallel execution: Faster test runs
Caching: Avoid redundant work

📊 Detailed Insights

Real-time progress: Live test execution
Performance metrics: Timing and resource usage
Trend analysis: Historical test data
Quality metrics: Coverage and success rates

🚀 Developer Friendly

Easy integration: CI/CD, pre-commit hooks
Flexible configuration: Customizable behavior
Rich reporting: Multiple output formats
Debug support: Detailed error information

The comprehensive testing system provides complete test coverage with intelligent automation and detailed reporting, ensuring code quality and reliability across the entire MAx Framework!

Install tests and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

# /tests - Comprehensive Testing System Manage, run, and analyze all tests across the MAx Framework with comprehensive reporting and debugging capabilities. ## Usage ```bash # Run all tests with comprehensive reporting /tests # Run specific test category /tests --category unit /tests --category integration /tests --category system # Run tests with specific focus /tests --focus contracts /tests --focus commands /tests --focus quality # Run tests with detailed output /tests --verbose # Run tests with auto-fix enabled /tests --auto-fix # Generate test report /tests --report # Quick test run /tests --quick ``` ## Test Categories ### 🧪 **Unit Tests** - **Individual component testing** - **Function and method validation** - **Class and module testing** - **Edge case coverage** ### 🔗 **Integration Tests** - **Component interaction testing** - **Cross-module functionality** - **API integration validation** - **Workflow testing** ### 🏗️ **System Tests** - **End-to-end workflows** - **Framework integration** - **Performance validation** - **User scenario testing** ### 📋 **Contract Tests** - **AI contract validation** - **Code quality standards** - **Performance contracts** - **Security contracts** ## Test Focus Areas ### 🎯 **Contracts Focus** ```bash /tests --focus contracts ``` - AI contract compliance - Code quality standards - Performance benchmarks - Security validations ### ⚡ **Commands Focus** ```bash /tests --focus commands ``` - Command execution testing - Argument parsing validation - Error handling verification - Integration testing ### 🔍 **Quality Focus** ```bash /tests --focus quality ``` - Code quality metrics - Style guide compliance - Documentation coverage - Best practices validation ## Test Execution Options ### 📊 **Comprehensive Mode** ```bash /tests ``` - **All test categories** - **Detailed reporting** - **Performance metrics** - **Coverage analysis** - **Error categorization** ### ⚡ **Quick Mode** ```bash /tests --quick ``` - **Essential tests only** - **Minimal output** - **Fast execution** - **Basic reporting** ### 🔧 **Auto-Fix Mode** ```bash /tests --auto-fix ``` - **Automatic error fixing** - **Import resolution** - **Syntax correction** - **Missing method addition** ### 📋 **Report Mode** ```bash /tests --report ``` - **Detailed test report** - **Coverage statistics** - **Performance analysis** - **Trend tracking** ## Test Discovery ### 🔍 **Test File Patterns** - `test_*.py` - Unit test files - `*_test.py` - Alternative test naming - `tests/**/*.py` - Test directory structure - `**/test_*.py` - Recursive discovery ### 📁 **Test Directory Structure** ``` tests/ ├── unit/ # Unit tests │ ├── test_commands.py │ ├── test_quality.py │ └── test_contracts.py ├── integration/ # Integration tests │ ├── test_workflows.py │ ├── test_systems.py │ └── test_apis.py ├── system/ # System tests │ ├── test_end_to_end.py │ ├── test_performance.py │ └── test_user_scenarios.py └── reports/ # Test reports ├── coverage.json ├── results.json └── trends.json ``` ## Test Results ### 📊 **Success Metrics** ```bash ✅ PASSED: 42 tests (85%) ⚠️ SKIPPED: 5 tests (10%) ❌ FAILED: 3 tests (5%) ⏱️ Duration: 2.34s 📊 Coverage: 87.3% ``` ### 🚨 **Failure Analysis** ```bash ❌ FAILED TESTS: 1. test_command_execution - Error: AssertionError - Location: tests/commands/test_commands.py:42 - Message: Expected success but got error 2. test_contract_validation - Error: ImportError - Location: tests/contracts/test_ai.py:15 - Message: Missing required import 3. test_quality_metrics - Error: TimeoutError - Location: tests/quality/test_metrics.py:78 - Message: Test exceeded 30s timeout ``` ### 🔧 **Auto-Fix Results** ```bash 🔧 APPLIED FIXES: 1. Added missing import: import unittest 2. Fixed syntax error: print statement 3. Added missing method: setUp() 4. Corrected indentation: 4 spaces ``` ## Configuration ### ⚙️ **Test Configuration** ```json { "test_paths": ["tests/", "test_*.py", "*_test.py"], "test_categories": ["unit", "integration", "system", "contracts"], "timeout": 30, "auto_fix": true, "verbose": true, "coverage": true, "parallel": true } ``` ### 🎯 **Environment Variables** ```bash # Enable auto-fix export MAX_TESTS_AUTO_FIX=1 # Set test timeout export MAX_TESTS_TIMEOUT=60 # Enable verbose output export MAX_TESTS_VERBOSE=1 # Disable parallel execution export MAX_TESTS_SEQUENTIAL=1 ``` ## Integration ### 🔄 **CI/CD Integration** ```yaml # .github/workflows/tests.yml name: Comprehensive Tests on: [push, pull_request] jobs: test: runs-on: ubuntu-latest steps: - uses: actions/checkout@v2 - name: Run comprehensive tests run: /tests --report - name: Upload test results uses: actions/upload-artifact@v2 with: name: test-results path: tests/reports/ ``` ### 🔧 **Pre-commit Hook** ```bash #!/bin/sh # .git/hooks/pre-commit /tests --quick if [ $? -ne 0 ]; then echo "❌ Tests failed - commit blocked" exit 1 fi ``` ### 📊 **Quality Gate Integration** ```bash # Run as part of quality gate /max-quality --include-tests # Fail build on test failures /tests --strict ``` ## Advanced Features ### 🎯 **Test Filtering** ```bash # Run tests matching pattern /tests --pattern "test_*contract*" # Exclude specific tests /tests --exclude "test_slow_*" # Run tests by file /tests --file test_commands.py # Run tests by directory /tests --directory tests/unit/ ``` ### 📈 **Performance Testing** ```bash # Run performance benchmarks /tests --performance # Measure execution time /tests --timing # Memory usage analysis /tests --memory ``` ### 🔍 **Debug Mode** ```bash # Run with debugger /tests --debug # Stop on first failure /tests --failfast # Run with detailed tracebacks /tests --traceback ``` ## Reports ### 📊 **Coverage Report** ```bash /tests --coverage ``` - **Line coverage**: 87.3% - **Branch coverage**: 82.1% - **Function coverage**: 91.5% - **Missing coverage**: 12.7% ### 📈 **Trend Analysis** ```bash /tests --trends ``` - **Test count trend**: +5 tests this week - **Success rate trend**: 92% → 95% - **Performance trend**: -0.2s average - **Coverage trend**: +2.3% this month ### 📋 **Detailed Report** ```bash /tests --report --detailed ``` - **Test execution summary** - **Failure analysis** - **Performance metrics** - **Coverage breakdown** - **Recommendations** ## Benefits ### 🎯 **Comprehensive Coverage** - **All test types**: Unit, integration, system, contracts - **Multiple frameworks**: unittest, pytest, custom - **Cross-platform**: Linux, macOS, Windows - **Language support**: Python, JavaScript, Shell ### 🔧 **Intelligent Testing** - **Auto-fix capabilities**: Common error resolution - **Smart discovery**: Automatic test finding - **Parallel execution**: Faster test runs - **Caching**: Avoid redundant work ### 📊 **Detailed Insights** - **Real-time progress**: Live test execution - **Performance metrics**: Timing and resource usage - **Trend analysis**: Historical test data - **Quality metrics**: Coverage and success rates ### 🚀 **Developer Friendly** - **Easy integration**: CI/CD, pre-commit hooks - **Flexible configuration**: Customizable behavior - **Rich reporting**: Multiple output formats - **Debug support**: Detailed error information The comprehensive testing system provides complete test coverage with intelligent automation and detailed reporting, ensuring code quality and reliability across the entire MAx Framework!

{ "prompt": "# /tests - Comprehensive Testing System\n\nManage, run, and analyze all tests across the MAx Framework with comprehensive reporting and debugging capabilities.\n\n## Usage\n\n```bash\n# Run all tests with comprehensive reporting\n/tests\n\n# Run specific test category\n/tests --category unit\n/tests --category integration\n/tests --category system\n\n# Run tests with specific focus\n/tests --focus contracts\n/tests --focus commands\n/tests --focus quality\n\n# Run tests with detailed output\n/tests --verbose\n\n# Run tests with auto-fix enabled\n/tests --auto-fix\n\n# Generate test report\n/tests --report\n\n# Quick test run\n/tests --quick\n```\n\n## Test Categories\n\n### 🧪 **Unit Tests**\n- **Individual component testing**\n- **Function and method validation**\n- **Class and module testing**\n- **Edge case coverage**\n\n### 🔗 **Integration Tests**\n- **Component interaction testing**\n- **Cross-module functionality**\n- **API integration validation**\n- **Workflow testing**\n\n### 🏗️ **System Tests**\n- **End-to-end workflows**\n- **Framework integration**\n- **Performance validation**\n- **User scenario testing**\n\n### 📋 **Contract Tests**\n- **AI contract validation**\n- **Code quality standards**\n- **Performance contracts**\n- **Security contracts**\n\n## Test Focus Areas\n\n### 🎯 **Contracts Focus**\n```bash\n/tests --focus contracts\n```\n- AI contract compliance\n- Code quality standards\n- Performance benchmarks\n- Security validations\n\n### ⚡ **Commands Focus**\n```bash\n/tests --focus commands\n```\n- Command execution testing\n- Argument parsing validation\n- Error handling verification\n- Integration testing\n\n### 🔍 **Quality Focus**\n```bash\n/tests --focus quality\n```\n- Code quality metrics\n- Style guide compliance\n- Documentation coverage\n- Best practices validation\n\n## Test Execution Options\n\n### 📊 **Comprehensive Mode**\n```bash\n/tests\n```\n- **All test categories**\n- **Detailed reporting**\n- **Performance metrics**\n- **Coverage analysis**\n- **Error categorization**\n\n### ⚡ **Quick Mode**\n```bash\n/tests --quick\n```\n- **Essential tests only**\n- **Minimal output**\n- **Fast execution**\n- **Basic reporting**\n\n### 🔧 **Auto-Fix Mode**\n```bash\n/tests --auto-fix\n```\n- **Automatic error fixing**\n- **Import resolution**\n- **Syntax correction**\n- **Missing method addition**\n\n### 📋 **Report Mode**\n```bash\n/tests --report\n```\n- **Detailed test report**\n- **Coverage statistics**\n- **Performance analysis**\n- **Trend tracking**\n\n## Test Discovery\n\n### 🔍 **Test File Patterns**\n- `test_*.py` - Unit test files\n- `*_test.py` - Alternative test naming\n- `tests/**/*.py` - Test directory structure\n- `**/test_*.py` - Recursive discovery\n\n### 📁 **Test Directory Structure**\n```\ntests/\n├── unit/ # Unit tests\n│ ├── test_commands.py\n│ ├── test_quality.py\n│ └── test_contracts.py\n├── integration/ # Integration tests\n│ ├── test_workflows.py\n│ ├── test_systems.py\n│ └── test_apis.py\n├── system/ # System tests\n│ ├── test_end_to_end.py\n│ ├── test_performance.py\n│ └── test_user_scenarios.py\n└── reports/ # Test reports\n ├── coverage.json\n ├── results.json\n └── trends.json\n```\n\n## Test Results\n\n### 📊 **Success Metrics**\n```bash\n✅ PASSED: 42 tests (85%)\n⚠️ SKIPPED: 5 tests (10%)\n❌ FAILED: 3 tests (5%)\n⏱️ Duration: 2.34s\n📊 Coverage: 87.3%\n```\n\n### 🚨 **Failure Analysis**\n```bash\n❌ FAILED TESTS:\n1. test_command_execution\n - Error: AssertionError\n - Location: tests/commands/test_commands.py:42\n - Message: Expected success but got error\n\n2. test_contract_validation\n - Error: ImportError\n - Location: tests/contracts/test_ai.py:15\n - Message: Missing required import\n\n3. test_quality_metrics\n - Error: TimeoutError\n - Location: tests/quality/test_metrics.py:78\n - Message: Test exceeded 30s timeout\n```\n\n### 🔧 **Auto-Fix Results**\n```bash\n🔧 APPLIED FIXES:\n1. Added missing import: import unittest\n2. Fixed syntax error: print statement\n3. Added missing method: setUp()\n4. Corrected indentation: 4 spaces\n```\n\n## Configuration\n\n### ⚙️ **Test Configuration**\n```json\n{\n \"test_paths\": [\"tests/\", \"test_*.py\", \"*_test.py\"],\n \"test_categories\": [\"unit\", \"integration\", \"system\", \"contracts\"],\n \"timeout\": 30,\n \"auto_fix\": true,\n \"verbose\": true,\n \"coverage\": true,\n \"parallel\": true\n}\n```\n\n### 🎯 **Environment Variables**\n```bash\n# Enable auto-fix\nexport MAX_TESTS_AUTO_FIX=1\n\n# Set test timeout\nexport MAX_TESTS_TIMEOUT=60\n\n# Enable verbose output\nexport MAX_TESTS_VERBOSE=1\n\n# Disable parallel execution\nexport MAX_TESTS_SEQUENTIAL=1\n```\n\n## Integration\n\n### 🔄 **CI/CD Integration**\n```yaml\n# .github/workflows/tests.yml\nname: Comprehensive Tests\non: [push, pull_request]\njobs:\n test:\n runs-on: ubuntu-latest\n steps:\n - uses: actions/checkout@v2\n - name: Run comprehensive tests\n run: /tests --report\n - name: Upload test results\n uses: actions/upload-artifact@v2\n with:\n name: test-results\n path: tests/reports/\n```\n\n### 🔧 **Pre-commit Hook**\n```bash\n#!/bin/sh\n# .git/hooks/pre-commit\n/tests --quick\nif [ $? -ne 0 ]; then\n echo \"❌ Tests failed - commit blocked\"\n exit 1\nfi\n```\n\n### 📊 **Quality Gate Integration**\n```bash\n# Run as part of quality gate\n/max-quality --include-tests\n\n# Fail build on test failures\n/tests --strict\n```\n\n## Advanced Features\n\n### 🎯 **Test Filtering**\n```bash\n# Run tests matching pattern\n/tests --pattern \"test_*contract*\"\n\n# Exclude specific tests\n/tests --exclude \"test_slow_*\"\n\n# Run tests by file\n/tests --file test_commands.py\n\n# Run tests by directory\n/tests --directory tests/unit/\n```\n\n### 📈 **Performance Testing**\n```bash\n# Run performance benchmarks\n/tests --performance\n\n# Measure execution time\n/tests --timing\n\n# Memory usage analysis\n/tests --memory\n```\n\n### 🔍 **Debug Mode**\n```bash\n# Run with debugger\n/tests --debug\n\n# Stop on first failure\n/tests --failfast\n\n# Run with detailed tracebacks\n/tests --traceback\n```\n\n## Reports\n\n### 📊 **Coverage Report**\n```bash\n/tests --coverage\n```\n- **Line coverage**: 87.3%\n- **Branch coverage**: 82.1%\n- **Function coverage**: 91.5%\n- **Missing coverage**: 12.7%\n\n### 📈 **Trend Analysis**\n```bash\n/tests --trends\n```\n- **Test count trend**: +5 tests this week\n- **Success rate trend**: 92% → 95%\n- **Performance trend**: -0.2s average\n- **Coverage trend**: +2.3% this month\n\n### 📋 **Detailed Report**\n```bash\n/tests --report --detailed\n```\n- **Test execution summary**\n- **Failure analysis**\n- **Performance metrics**\n- **Coverage breakdown**\n- **Recommendations**\n\n## Benefits\n\n### 🎯 **Comprehensive Coverage**\n- **All test types**: Unit, integration, system, contracts\n- **Multiple frameworks**: unittest, pytest, custom\n- **Cross-platform**: Linux, macOS, Windows\n- **Language support**: Python, JavaScript, Shell\n\n### 🔧 **Intelligent Testing**\n- **Auto-fix capabilities**: Common error resolution\n- **Smart discovery**: Automatic test finding\n- **Parallel execution**: Faster test runs\n- **Caching**: Avoid redundant work\n\n### 📊 **Detailed Insights**\n- **Real-time progress**: Live test execution\n- **Performance metrics**: Timing and resource usage\n- **Trend analysis**: Historical test data\n- **Quality metrics**: Coverage and success rates\n\n### 🚀 **Developer Friendly**\n- **Easy integration**: CI/CD, pre-commit hooks\n- **Flexible configuration**: Customizable behavior\n- **Rich reporting**: Multiple output formats\n- **Debug support**: Detailed error information\n\nThe comprehensive testing system provides complete test coverage with intelligent automation and detailed reporting, ensuring code quality and reliability across the entire MAx Framework!", "variables": [], "notes": "Comprehensive testing system and test management for MAx Framework", "metadata": { "source": { "provider": "github-windsurf-workflows", "repository": "https://github.com/danilonovaisv/PROMPT-APP", "path": ".windsurf/workflows/tests.md", "ref": "949bfc4088d7fceb3282e46883894fde4798efd1", "url": "https://github.com/danilonovaisv/PROMPT-APP/blob/949bfc4088d7fceb3282e46883894fde4798efd1/.windsurf/workflows/tests.md", "key": "danilonovaisv/PROMPT-APP/.windsurf/workflows/tests.md" } } }