rpa_vision_v3/examples/test_phase7_learning.py

#!/usr/bin/env python3
"""Test Phase 7 - Learning System"""
import sys
from pathlib import Path
sys.path.insert(0, str(Path(__file__).parent.parent))
import logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

def test_imports():
    logger.info("\n=== Testing Imports ===")
    try:
        from core.learning.learning_manager import LearningManager, WorkflowStats
        logger.info("✓ LearningManager imported")
        from core.learning.feedback_processor import FeedbackProcessor, FeedbackType
        logger.info("✓ FeedbackProcessor imported")
        from core.models.workflow_graph import LearningState
        logger.info("✓ LearningState imported")
        return True
    except Exception as e:
        logger.error(f"✗ Import failed: {e}")
        return False

def test_learning_manager():
    logger.info("\n=== Testing LearningManager ===")
    try:
        from core.learning.learning_manager import LearningManager
        from core.models.workflow_graph import Workflow, LearningState
        
        manager = LearningManager()
        logger.info("✓ LearningManager created")
        
        # Create test workflow
        workflow = Workflow(
            id="test_workflow_1",
            name="Test Workflow",
            learning_state=LearningState.OBSERVATION
        )
        
        manager.register_workflow(workflow)
        logger.info(f"✓ Workflow registered: {workflow.id}")
        
        # Test state transitions
        logger.info("\n  Testing state transitions:")
        
        # OBSERVATION → COACHING (need 5 observations with confidence > 0.90)
        for i in range(5):
            manager.record_observation(workflow.id)
            manager.workflows[workflow.id].confidence_scores.append(0.92)
        
        state = manager.get_workflow_state(workflow.id)
        logger.info(f"  After 5 observations: {state.value}")
        
        # COACHING → AUTO_CANDIDATE (need 10 executions with success > 0.90)
        for i in range(10):
            manager.record_execution(workflow.id, success=True, confidence=0.93)
        
        state = manager.get_workflow_state(workflow.id)
        logger.info(f"  After 10 successful executions: {state.value}")
        
        # AUTO_CANDIDATE → AUTO_CONFIRMED (need 20 executions with success > 0.95)
        for i in range(10):
            manager.record_execution(workflow.id, success=True, confidence=0.96)
        
        state = manager.get_workflow_state(workflow.id)
        logger.info(f"  After 20 total executions: {state.value}")
        
        stats = manager.get_workflow_stats(workflow.id)
        logger.info(f"  Final stats: success_rate={stats.success_rate:.2f}, avg_confidence={stats.avg_confidence:.2f}")
        
        return True
    except Exception as e:
        logger.error(f"✗ LearningManager test failed: {e}", exc_info=True)
        return False

def test_feedback_processor():
    logger.info("\n=== Testing FeedbackProcessor ===")
    try:
        from core.learning.feedback_processor import FeedbackProcessor, FeedbackType
        
        processor = FeedbackProcessor()
        logger.info("✓ FeedbackProcessor created")
        
        # Process different types of feedback
        result = processor.process_feedback(
            workflow_id="test_workflow_1",
            execution_id="exec_1",
            feedback_type=FeedbackType.CORRECT,
            confidence=0.95
        )
        logger.info(f"✓ CORRECT feedback processed: {len(result['suggestions'])} suggestions")
        
        result = processor.process_feedback(
            workflow_id="test_workflow_1",
            execution_id="exec_2",
            feedback_type=FeedbackType.INCORRECT,
            confidence=0.75,
            comment="Wrong button clicked"
        )
        logger.info(f"✓ INCORRECT feedback processed: {len(result['suggestions'])} suggestions")
        
        # Get stats
        stats = processor.get_feedback_stats("test_workflow_1")
        logger.info(f"✓ Feedback stats: {stats['total']} total, accuracy={stats['accuracy']:.2f}")
        
        return True
    except Exception as e:
        logger.error(f"✗ FeedbackProcessor test failed: {e}", exc_info=True)
        return False

def test_rollback():
    logger.info("\n=== Testing Rollback Mechanism ===")
    try:
        from core.learning.learning_manager import LearningManager
        from core.models.workflow_graph import Workflow, LearningState
        
        manager = LearningManager()
        
        # Create workflow in AUTO_CONFIRMED state
        workflow = Workflow(
            id="test_workflow_rollback",
            name="Rollback Test",
            learning_state=LearningState.AUTO_CONFIRMED
        )
        manager.register_workflow(workflow)
        manager.workflows[workflow.id].learning_state = LearningState.AUTO_CONFIRMED
        manager.workflows[workflow.id].execution_count = 25
        
        logger.info(f"  Initial state: {manager.get_workflow_state(workflow.id).value}")
        
        # Simulate confidence drop
        for i in range(10):
            manager.record_execution(workflow.id, success=False, confidence=0.70)
        
        state = manager.get_workflow_state(workflow.id)
        logger.info(f"  After confidence drop: {state.value}")
        
        if state == LearningState.COACHING:
            logger.info("✓ Rollback triggered successfully")
            return True
        else:
            logger.warning("✗ Rollback not triggered")
            return False
            
    except Exception as e:
        logger.error(f"✗ Rollback test failed: {e}", exc_info=True)
        return False

def main():
    logger.info("=" * 60)
    logger.info("Phase 7 - Learning System Tests")
    logger.info("=" * 60)
    
    tests = [
        test_imports,
        test_learning_manager,
        test_feedback_processor,
        test_rollback
    ]
    
    results = []
    for test in tests:
        try:
            result = test()
            results.append(result)
        except Exception as e:
            logger.error(f"Test {test.__name__} crashed: {e}", exc_info=True)
            results.append(False)
    
    passed = sum(results)
    logger.info(f"\n{'='*60}\nResults: {passed}/{len(results)} tests passed\n{'='*60}")
    return 0 if passed == len(results) else 1

if __name__ == '__main__':
    sys.exit(main())