Implement automatic AI analysis of feedback submissions using Claude API, including language detection, categorization, summarization, and translation to product owner's preferred language. Tasks Completed (T065-T092): - T065-T069: Unit tests for AI analyzer (5 tests) - T070: Integration test for full AI analysis workflow - T071: Created AIAnalyzer abstract base class interface - T072: Added AnalysisResult dataclass to feedback model - T073: Implemented ClaudeAnalyzer with Anthropic SDK - T074: Integrated Claude API with 45s timeout - T075: Designed single-call analysis prompt - T076: Language detection implementation - T077: Category extraction with validation - T078: Summary generation (1-2 sentences) - T079: Translation extraction - T080: Timeout handling for Claude API - T081: API error handling with proper exceptions - T082: Analysis storage to analysis.md file - T083: Formatted markdown output for analysis - T084: Background analysis trigger on submission - T085: Non-blocking async analysis via threading - T086: Status update to 'analyzing' before analysis - T087: Status update to 'analyzed' on success - T088: Status update to 'analysis_failed' on error - T089: Metadata update with category and language - T090: Environment configuration for ANTHROPIC_API_KEY - T091: Verification that original content.txt preserved (FR-016) - T092: Verification that images not analyzed via OCR (FR-021) Features: - Abstract AIAnalyzer interface for multiple AI providers - ClaudeAnalyzer implementation using Anthropic API - Background threading for non-blocking analysis - Flask app context management in background threads - Comprehensive error handling and status tracking - Original content preservation (FR-016 compliance) - Image storage without OCR (FR-021 compliance) Testing: - 5 unit tests for AI analyzer components - 2 integration tests for full analysis workflow - All 46 tests passing (1 skipped) - Mock-based testing to avoid API calls Files Changed: - app/models/feedback.py: Added AnalysisResult dataclass - app/routes/submission.py: Background analysis integration - app/services/ai_analyzer.py: NEW - AI analysis service - app/services/feedback_storage.py: Analysis storage methods - tests/unit/test_ai_analyzer.py: NEW - Unit tests (5 tests) - tests/integration/test_ai_analysis_flow.py: NEW - Integration tests (2 tests) - tests/integration/test_feedback_submission_flow.py: Threading mock added 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
163 lines
5.6 KiB
Python
163 lines
5.6 KiB
Python
"""Unit tests for AI analyzer"""
|
|
import pytest
|
|
from unittest.mock import Mock, patch, MagicMock
|
|
from app.services.ai_analyzer import AIAnalyzer, ClaudeAnalyzer
|
|
from app.models.feedback import AnalysisResult
|
|
|
|
|
|
@pytest.mark.unit
|
|
def test_ai_analyzer_interface():
|
|
"""T065: Unit test for AIAnalyzer interface
|
|
|
|
Verify that AIAnalyzer is an abstract base class
|
|
that cannot be instantiated directly
|
|
"""
|
|
with pytest.raises(TypeError):
|
|
# Should not be able to instantiate abstract base class
|
|
AIAnalyzer()
|
|
|
|
|
|
@pytest.mark.unit
|
|
def test_claude_analyzer_categorization(app):
|
|
"""T066: Unit test for ClaudeAnalyzer categorization
|
|
|
|
Verify that ClaudeAnalyzer correctly extracts category from AI response
|
|
"""
|
|
with app.app_context():
|
|
# Mock the Anthropic client to avoid initialization issues
|
|
with patch('app.services.ai_analyzer.anthropic.Anthropic'):
|
|
analyzer = ClaudeAnalyzer(api_key='test-key')
|
|
|
|
# Mock AI response with category
|
|
mock_response = Mock()
|
|
mock_response.content = [Mock(text="""
|
|
# Feedback Analysis
|
|
|
|
**Category**: bug
|
|
|
|
**Original Language**: en
|
|
|
|
**Summary**: User reports login issue
|
|
|
|
**Translation**: (same as original)
|
|
""")]
|
|
|
|
with patch.object(analyzer, '_call_claude_api', return_value=mock_response):
|
|
result = analyzer.analyze_feedback(
|
|
feedback_text="Login button doesn't work",
|
|
target_language='en',
|
|
product_id='test-product'
|
|
)
|
|
|
|
assert result.category == 'bug'
|
|
|
|
|
|
@pytest.mark.unit
|
|
def test_claude_analyzer_translation(app):
|
|
"""T067: Unit test for ClaudeAnalyzer translation
|
|
|
|
Verify that ClaudeAnalyzer correctly translates feedback
|
|
"""
|
|
with app.app_context():
|
|
# Mock the Anthropic client to avoid initialization issues
|
|
with patch('app.services.ai_analyzer.anthropic.Anthropic'):
|
|
analyzer = ClaudeAnalyzer(api_key='test-key')
|
|
|
|
# Mock AI response with translation
|
|
mock_response = Mock()
|
|
mock_response.content = [Mock(text="""
|
|
# Feedback Analysis
|
|
|
|
**Category**: feature_request
|
|
|
|
**Original Language**: de
|
|
|
|
**Summary**: User wants dark mode
|
|
|
|
**Translation**: I would like to have a dark mode for the application
|
|
""")]
|
|
|
|
with patch.object(analyzer, '_call_claude_api', return_value=mock_response):
|
|
result = analyzer.analyze_feedback(
|
|
feedback_text="Ich hätte gerne einen Dark Mode für die Anwendung",
|
|
target_language='en',
|
|
product_id='test-product'
|
|
)
|
|
|
|
assert result.translation == 'I would like to have a dark mode for the application'
|
|
assert result.original_language == 'de'
|
|
|
|
|
|
@pytest.mark.unit
|
|
def test_claude_analyzer_summary_generation(app):
|
|
"""T068: Unit test for ClaudeAnalyzer summary generation
|
|
|
|
Verify that ClaudeAnalyzer generates concise summaries
|
|
"""
|
|
with app.app_context():
|
|
# Mock the Anthropic client to avoid initialization issues
|
|
with patch('app.services.ai_analyzer.anthropic.Anthropic'):
|
|
analyzer = ClaudeAnalyzer(api_key='test-key')
|
|
|
|
# Mock AI response with summary
|
|
mock_response = Mock()
|
|
mock_response.content = [Mock(text="""
|
|
# Feedback Analysis
|
|
|
|
**Category**: complaint
|
|
|
|
**Original Language**: en
|
|
|
|
**Summary**: User experienced slow page load times during peak hours
|
|
|
|
**Translation**: (same as original)
|
|
""")]
|
|
|
|
with patch.object(analyzer, '_call_claude_api', return_value=mock_response):
|
|
long_feedback = """
|
|
I've been using your service for three months now, and I have to say
|
|
I'm quite disappointed with the performance during peak hours. Yesterday
|
|
evening around 8 PM, I tried to load the dashboard multiple times and
|
|
each time it took over 30 seconds. This is unacceptable for a paid service.
|
|
"""
|
|
|
|
result = analyzer.analyze_feedback(
|
|
feedback_text=long_feedback,
|
|
target_language='en',
|
|
product_id='test-product'
|
|
)
|
|
|
|
assert result.summary == 'User experienced slow page load times during peak hours'
|
|
assert len(result.summary) < len(long_feedback)
|
|
|
|
|
|
@pytest.mark.unit
|
|
def test_analysis_error_handling(app):
|
|
"""T069: Unit test for analysis error handling
|
|
|
|
Verify that ClaudeAnalyzer handles API errors gracefully
|
|
"""
|
|
with app.app_context():
|
|
# Mock the Anthropic client to avoid initialization issues
|
|
with patch('app.services.ai_analyzer.anthropic.Anthropic'):
|
|
analyzer = ClaudeAnalyzer(api_key='test-key')
|
|
|
|
# Test API timeout
|
|
with patch.object(analyzer, '_call_claude_api', side_effect=TimeoutError("API timeout")):
|
|
with pytest.raises(Exception) as exc_info:
|
|
analyzer.analyze_feedback(
|
|
feedback_text="Test feedback",
|
|
target_language='en',
|
|
product_id='test-product'
|
|
)
|
|
assert "timeout" in str(exc_info.value).lower() or "API" in str(exc_info.value)
|
|
|
|
# Test API error
|
|
with patch.object(analyzer, '_call_claude_api', side_effect=Exception("API Error")):
|
|
with pytest.raises(Exception):
|
|
analyzer.analyze_feedback(
|
|
feedback_text="Test feedback",
|
|
target_language='en',
|
|
product_id='test-product'
|
|
)
|