Fix YAML validator and activity file validation errors
- Updated validator terminal step detection to only flag truly terminal steps - Fixed validator to accept integers and booleans in buckets (as supported by app.py) - Fixed metadata_remove format in activity17 from dictionary to list of strings - Added proper terminal section to activity3.yaml without questions/buckets - Fixed missing restart transition and bucket in activity28 - Removed unused game_end transitions from battleship files - Updated exit transitions to go directly to step_4 (goodbye step) - Applied black formatting to validator code All 30 activity YAML files now validate successfully with 0 errors and 0 warnings.
This commit is contained in:
parent
d4a075ac9a
commit
51b74be7d9
12 changed files with 1073 additions and 780 deletions
|
|
@ -4,7 +4,7 @@ Unit tests for the activity_yaml_validator.py module.
|
|||
|
||||
Tests all validation features including:
|
||||
- YAML syntax validation
|
||||
- Structure validation
|
||||
- Structure validation
|
||||
- Metadata operations validation
|
||||
- Python code validation
|
||||
- Logic flow validation
|
||||
|
|
@ -24,22 +24,22 @@ from activity_yaml_validator import ActivityYAMLValidator, ValidationError
|
|||
|
||||
class TestActivityYAMLValidator(unittest.TestCase):
|
||||
"""Test cases for ActivityYAMLValidator"""
|
||||
|
||||
|
||||
def setUp(self):
|
||||
"""Set up test fixtures"""
|
||||
self.validator = ActivityYAMLValidator()
|
||||
|
||||
|
||||
def create_temp_yaml(self, content: str) -> str:
|
||||
"""Create a temporary YAML file with given content"""
|
||||
with tempfile.NamedTemporaryFile(mode='w', suffix='.yaml', delete=False) as f:
|
||||
with tempfile.NamedTemporaryFile(mode="w", suffix=".yaml", delete=False) as f:
|
||||
f.write(content)
|
||||
return f.name
|
||||
|
||||
|
||||
def tearDown(self):
|
||||
"""Clean up any temporary files"""
|
||||
# Clean up is handled by tempfile
|
||||
pass
|
||||
|
||||
|
||||
def test_valid_yaml_passes(self):
|
||||
"""Test that a valid YAML file passes validation"""
|
||||
valid_yaml = """
|
||||
|
|
@ -80,7 +80,7 @@ sections:
|
|||
self.assertEqual(len(errors), 0)
|
||||
finally:
|
||||
os.unlink(temp_file)
|
||||
|
||||
|
||||
def test_yaml_syntax_error(self):
|
||||
"""Test that YAML syntax errors are caught"""
|
||||
invalid_yaml = """
|
||||
|
|
@ -102,7 +102,7 @@ sections:
|
|||
self.assertIn("YAML syntax error", errors[0])
|
||||
finally:
|
||||
os.unlink(temp_file)
|
||||
|
||||
|
||||
def test_missing_required_fields(self):
|
||||
"""Test that missing required fields are caught"""
|
||||
missing_sections = """
|
||||
|
|
@ -115,7 +115,7 @@ default_max_attempts_per_step: 3
|
|||
self.assertIn("Missing required field: sections", errors)
|
||||
finally:
|
||||
os.unlink(temp_file)
|
||||
|
||||
|
||||
def test_invalid_field_types(self):
|
||||
"""Test that invalid field types are caught"""
|
||||
invalid_types = """
|
||||
|
|
@ -131,11 +131,13 @@ sections:
|
|||
try:
|
||||
is_valid, errors, warnings = self.validator.validate_file(temp_file)
|
||||
self.assertFalse(is_valid)
|
||||
self.assertTrue(any("must be a positive integer" in error for error in errors))
|
||||
self.assertTrue(
|
||||
any("must be a positive integer" in error for error in errors)
|
||||
)
|
||||
self.assertTrue(any("must be a string" in error for error in errors))
|
||||
finally:
|
||||
os.unlink(temp_file)
|
||||
|
||||
|
||||
def test_duplicate_ids(self):
|
||||
"""Test that duplicate section and step IDs are caught"""
|
||||
duplicate_ids = """
|
||||
|
|
@ -168,16 +170,40 @@ sections:
|
|||
self.assertTrue(any("Duplicate step_id" in error for error in errors))
|
||||
finally:
|
||||
os.unlink(temp_file)
|
||||
|
||||
|
||||
def test_terminal_step_validation(self):
|
||||
"""Test that terminal steps cannot have questions or buckets"""
|
||||
terminal_with_question = """
|
||||
sections:
|
||||
- section_id: "section_1"
|
||||
title: "Test"
|
||||
title: "First Section"
|
||||
steps:
|
||||
- step_id: "terminal_step"
|
||||
title: "Final Step"
|
||||
- step_id: "step_1"
|
||||
title: "First Step"
|
||||
content_blocks:
|
||||
- "This step is fine"
|
||||
- step_id: "step_2"
|
||||
title: "Also fine"
|
||||
question: "Questions are OK in non-terminal steps"
|
||||
buckets: ["yes", "no"]
|
||||
transitions:
|
||||
yes:
|
||||
content_blocks: ["Good"]
|
||||
next_section_and_step: "section_2:step_1"
|
||||
no:
|
||||
content_blocks: ["Try again"]
|
||||
- section_id: "section_2"
|
||||
title: "Last Section"
|
||||
steps:
|
||||
- step_id: "step_1"
|
||||
title: "Not terminal - has another step after"
|
||||
question: "This is OK"
|
||||
buckets: ["answer"]
|
||||
transitions:
|
||||
answer:
|
||||
content_blocks: ["Continue"]
|
||||
- step_id: "step_2"
|
||||
title: "This is the real terminal step"
|
||||
question: "This is invalid"
|
||||
buckets:
|
||||
- some_bucket
|
||||
|
|
@ -185,17 +211,24 @@ sections:
|
|||
some_bucket:
|
||||
content_blocks:
|
||||
- "Done"
|
||||
# No next_section_and_step makes this terminal
|
||||
# No next_section_and_step and last step of last section = terminal
|
||||
"""
|
||||
temp_file = self.create_temp_yaml(terminal_with_question)
|
||||
try:
|
||||
is_valid, errors, warnings = self.validator.validate_file(temp_file)
|
||||
self.assertFalse(is_valid)
|
||||
self.assertTrue(any("Final/terminal steps cannot have questions" in error for error in errors))
|
||||
self.assertTrue(any("Final/terminal steps should not have buckets" in error for error in errors))
|
||||
# Should only flag the last step of the last section
|
||||
terminal_errors = [e for e in errors if "Final/terminal" in e]
|
||||
self.assertEqual(len(terminal_errors), 2) # One for question, one for buckets
|
||||
self.assertTrue(
|
||||
any(
|
||||
"section_2" in error and "step_2" in error
|
||||
for error in terminal_errors
|
||||
)
|
||||
)
|
||||
finally:
|
||||
os.unlink(temp_file)
|
||||
|
||||
|
||||
def test_metadata_operations_validation(self):
|
||||
"""Test validation of metadata operations"""
|
||||
metadata_test = """
|
||||
|
|
@ -225,13 +258,27 @@ sections:
|
|||
try:
|
||||
is_valid, errors, warnings = self.validator.validate_file(temp_file)
|
||||
self.assertFalse(is_valid)
|
||||
self.assertTrue(any("metadata_clear' must be boolean" in error for error in errors))
|
||||
self.assertTrue(any("metadata_feedback_filter' must be a list" in error for error in errors))
|
||||
self.assertTrue(any("metadata_remove' must be a string or list of strings" in error for error in errors))
|
||||
self.assertTrue(any("metadata_add' must be a dictionary" in error for error in errors))
|
||||
self.assertTrue(
|
||||
any("metadata_clear' must be boolean" in error for error in errors)
|
||||
)
|
||||
self.assertTrue(
|
||||
any(
|
||||
"metadata_feedback_filter' must be a list" in error
|
||||
for error in errors
|
||||
)
|
||||
)
|
||||
self.assertTrue(
|
||||
any(
|
||||
"metadata_remove' must be a string or list of strings" in error
|
||||
for error in errors
|
||||
)
|
||||
)
|
||||
self.assertTrue(
|
||||
any("metadata_add' must be a dictionary" in error for error in errors)
|
||||
)
|
||||
finally:
|
||||
os.unlink(temp_file)
|
||||
|
||||
|
||||
def test_valid_metadata_operations(self):
|
||||
"""Test that valid metadata operations pass"""
|
||||
valid_metadata = """
|
||||
|
|
@ -280,7 +327,7 @@ sections:
|
|||
self.assertEqual(len(errors), 0)
|
||||
finally:
|
||||
os.unlink(temp_file)
|
||||
|
||||
|
||||
def test_python_syntax_validation(self):
|
||||
"""Test that Python syntax errors in scripts are caught"""
|
||||
python_syntax_error = """
|
||||
|
|
@ -316,7 +363,7 @@ sections:
|
|||
self.assertTrue(any("Python syntax error" in error for error in errors))
|
||||
finally:
|
||||
os.unlink(temp_file)
|
||||
|
||||
|
||||
def test_invalid_transitions(self):
|
||||
"""Test validation of transition references"""
|
||||
invalid_transitions = """
|
||||
|
|
@ -344,13 +391,20 @@ sections:
|
|||
is_valid, errors, warnings = self.validator.validate_file(temp_file)
|
||||
self.assertFalse(is_valid)
|
||||
# Should have errors for invalid transition targets and missing transitions
|
||||
self.assertTrue(any("Invalid transition target" in error for error in errors))
|
||||
self.assertTrue(any("must be in format 'section_id:step_id'" in error for error in errors))
|
||||
self.assertTrue(
|
||||
any("Invalid transition target" in error for error in errors)
|
||||
)
|
||||
self.assertTrue(
|
||||
any(
|
||||
"must be in format 'section_id:step_id'" in error
|
||||
for error in errors
|
||||
)
|
||||
)
|
||||
# Should have warnings for unused transitions
|
||||
self.assertTrue(any("Unused transition" in warning for warning in warnings))
|
||||
finally:
|
||||
os.unlink(temp_file)
|
||||
|
||||
|
||||
def test_metadata_feedback_filter_warning(self):
|
||||
"""Test warning when metadata_feedback_filter used without feedback_tokens_for_ai"""
|
||||
metadata_filter_no_feedback = """
|
||||
|
|
@ -378,10 +432,16 @@ sections:
|
|||
try:
|
||||
is_valid, errors, warnings = self.validator.validate_file(temp_file)
|
||||
self.assertTrue(is_valid) # Should be valid but with warning
|
||||
self.assertTrue(any("metadata_feedback_filter used but no feedback_tokens_for_ai" in warning for warning in warnings))
|
||||
self.assertTrue(
|
||||
any(
|
||||
"metadata_feedback_filter used but no feedback_tokens_for_ai"
|
||||
in warning
|
||||
for warning in warnings
|
||||
)
|
||||
)
|
||||
finally:
|
||||
os.unlink(temp_file)
|
||||
|
||||
|
||||
def test_pre_script_warning(self):
|
||||
"""Test warning when pre_script used without question"""
|
||||
pre_script_no_question = """
|
||||
|
|
@ -400,10 +460,15 @@ sections:
|
|||
try:
|
||||
is_valid, errors, warnings = self.validator.validate_file(temp_file)
|
||||
self.assertTrue(is_valid) # Should be valid but with warning
|
||||
self.assertTrue(any("pre_script typically used with question steps" in warning for warning in warnings))
|
||||
self.assertTrue(
|
||||
any(
|
||||
"pre_script typically used with question steps" in warning
|
||||
for warning in warnings
|
||||
)
|
||||
)
|
||||
finally:
|
||||
os.unlink(temp_file)
|
||||
|
||||
|
||||
def test_empty_else_block_detection(self):
|
||||
"""Test detection of empty else blocks in Python code"""
|
||||
empty_else_block = """
|
||||
|
|
@ -434,10 +499,12 @@ sections:
|
|||
try:
|
||||
is_valid, errors, warnings = self.validator.validate_file(temp_file)
|
||||
# This should detect the empty else block
|
||||
self.assertTrue(any("'else:' block contains only comments" in error for error in errors))
|
||||
self.assertTrue(
|
||||
any("'else:' block contains only comments" in error for error in errors)
|
||||
)
|
||||
finally:
|
||||
os.unlink(temp_file)
|
||||
|
||||
|
||||
def test_content_blocks_validation(self):
|
||||
"""Test validation of content_blocks structure"""
|
||||
invalid_content_blocks = """
|
||||
|
|
@ -460,11 +527,13 @@ sections:
|
|||
try:
|
||||
is_valid, errors, warnings = self.validator.validate_file(temp_file)
|
||||
self.assertFalse(is_valid)
|
||||
self.assertTrue(any("content_blocks must be a list" in error for error in errors))
|
||||
self.assertTrue(
|
||||
any("content_blocks must be a list" in error for error in errors)
|
||||
)
|
||||
self.assertTrue(any("must be a string" in error for error in errors))
|
||||
finally:
|
||||
os.unlink(temp_file)
|
||||
|
||||
|
||||
def test_transition_fields_validation(self):
|
||||
"""Test validation of various transition fields"""
|
||||
invalid_transition_fields = """
|
||||
|
|
@ -507,13 +576,24 @@ sections:
|
|||
try:
|
||||
is_valid, errors, warnings = self.validator.validate_file(temp_file)
|
||||
self.assertFalse(is_valid)
|
||||
self.assertTrue(any("run_processing_script' must be boolean" in error for error in errors))
|
||||
self.assertTrue(any("ai_feedback' must be a dictionary" in error for error in errors))
|
||||
self.assertTrue(any("tokens_for_ai must be a string" in error for error in errors))
|
||||
self.assertTrue(any("content_blocks' must be a list" in error for error in errors))
|
||||
self.assertTrue(
|
||||
any(
|
||||
"run_processing_script' must be boolean" in error
|
||||
for error in errors
|
||||
)
|
||||
)
|
||||
self.assertTrue(
|
||||
any("ai_feedback' must be a dictionary" in error for error in errors)
|
||||
)
|
||||
self.assertTrue(
|
||||
any("tokens_for_ai must be a string" in error for error in errors)
|
||||
)
|
||||
self.assertTrue(
|
||||
any("content_blocks' must be a list" in error for error in errors)
|
||||
)
|
||||
finally:
|
||||
os.unlink(temp_file)
|
||||
|
||||
|
||||
def test_using_existing_failing_fixture(self):
|
||||
"""Test using the existing failing fixture we created"""
|
||||
fixture_path = "tests/fixtures/test_invalid.yaml"
|
||||
|
|
@ -523,32 +603,45 @@ sections:
|
|||
self.assertGreater(len(errors), 0)
|
||||
# Should catch the YAML syntax error we know is in there
|
||||
self.assertTrue(any("YAML syntax error" in error for error in errors))
|
||||
|
||||
|
||||
def test_cli_integration(self):
|
||||
"""Test the command line interface"""
|
||||
import subprocess
|
||||
import sys
|
||||
|
||||
|
||||
# Test with valid battleship YAML
|
||||
result = subprocess.run([
|
||||
sys.executable, "activity_yaml_validator.py",
|
||||
"research/activity29-battleship.yaml"
|
||||
], capture_output=True, text=True, cwd=".")
|
||||
|
||||
result = subprocess.run(
|
||||
[
|
||||
sys.executable,
|
||||
"activity_yaml_validator.py",
|
||||
"research/activity29-battleship.yaml",
|
||||
],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
cwd=".",
|
||||
)
|
||||
|
||||
# Should succeed (exit code 0) despite warnings
|
||||
self.assertEqual(result.returncode, 0)
|
||||
self.assertIn("valid", result.stdout.lower())
|
||||
|
||||
|
||||
# Test with --strict flag (warnings become errors)
|
||||
result = subprocess.run([
|
||||
sys.executable, "activity_yaml_validator.py",
|
||||
"research/activity29-battleship.yaml", "--strict"
|
||||
], capture_output=True, text=True, cwd=".")
|
||||
|
||||
result = subprocess.run(
|
||||
[
|
||||
sys.executable,
|
||||
"activity_yaml_validator.py",
|
||||
"research/activity29-battleship.yaml",
|
||||
"--strict",
|
||||
],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
cwd=".",
|
||||
)
|
||||
|
||||
# Should fail (exit code 1) because warnings become errors in strict mode
|
||||
self.assertEqual(result.returncode, 1)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
if __name__ == "__main__":
|
||||
# Run the tests
|
||||
unittest.main(verbosity=2)
|
||||
unittest.main(verbosity=2)
|
||||
|
|
|
|||
|
|
@ -18,75 +18,88 @@ from pathlib import Path
|
|||
sys.path.insert(0, str(Path(__file__).parent.parent.parent))
|
||||
|
||||
# Mock external dependencies before importing app
|
||||
with patch.dict('sys.modules', {
|
||||
'gevent': MagicMock(),
|
||||
'flask_socketio': MagicMock(),
|
||||
'boto3': MagicMock(),
|
||||
'openai': MagicMock(),
|
||||
'together': MagicMock(),
|
||||
'models': MagicMock(),
|
||||
}):
|
||||
with patch.dict(
|
||||
"sys.modules",
|
||||
{
|
||||
"gevent": MagicMock(),
|
||||
"flask_socketio": MagicMock(),
|
||||
"boto3": MagicMock(),
|
||||
"openai": MagicMock(),
|
||||
"together": MagicMock(),
|
||||
"models": MagicMock(),
|
||||
},
|
||||
):
|
||||
import app
|
||||
|
||||
|
||||
class TestAppUtilityFunctions(unittest.TestCase):
|
||||
"""Test utility functions in app.py"""
|
||||
|
||||
|
||||
def setUp(self):
|
||||
"""Set up test fixtures"""
|
||||
self.test_app = app.app
|
||||
self.test_app.config['TESTING'] = True
|
||||
|
||||
self.test_app.config["TESTING"] = True
|
||||
|
||||
def test_get_client_for_endpoint(self):
|
||||
"""Test OpenAI client creation for endpoints"""
|
||||
with patch('app.OpenAI') as mock_openai:
|
||||
with patch("app.OpenAI") as mock_openai:
|
||||
mock_client = MagicMock()
|
||||
mock_openai.return_value = mock_client
|
||||
|
||||
|
||||
# Mock the actual function call
|
||||
with patch.object(app, 'get_client_for_endpoint', return_value=mock_client) as mock_func:
|
||||
with patch.object(
|
||||
app, "get_client_for_endpoint", return_value=mock_client
|
||||
) as mock_func:
|
||||
result = app.get_client_for_endpoint("https://test.api", "test-key")
|
||||
|
||||
|
||||
self.assertEqual(result, mock_client)
|
||||
mock_func.assert_called_once_with("https://test.api", "test-key")
|
||||
|
||||
|
||||
def test_get_client_for_model_existing(self):
|
||||
"""Test getting client for existing model"""
|
||||
test_client = MagicMock()
|
||||
test_base_url = "https://test.api"
|
||||
|
||||
|
||||
# Mock the function directly since MODEL_CLIENT_MAP is populated at import time
|
||||
with patch.object(app, 'get_client_for_model', return_value=test_client) as mock_func:
|
||||
result = app.get_client_for_model('test-model')
|
||||
|
||||
with patch.object(
|
||||
app, "get_client_for_model", return_value=test_client
|
||||
) as mock_func:
|
||||
result = app.get_client_for_model("test-model")
|
||||
|
||||
self.assertEqual(result, test_client)
|
||||
mock_func.assert_called_once_with('test-model')
|
||||
|
||||
mock_func.assert_called_once_with("test-model")
|
||||
|
||||
def test_get_client_for_model_nonexistent(self):
|
||||
"""Test getting client for non-existent model"""
|
||||
with patch.object(app, 'get_client_for_model', return_value=None) as mock_func:
|
||||
result = app.get_client_for_model('nonexistent-model')
|
||||
|
||||
with patch.object(app, "get_client_for_model", return_value=None) as mock_func:
|
||||
result = app.get_client_for_model("nonexistent-model")
|
||||
|
||||
self.assertIsNone(result)
|
||||
mock_func.assert_called_once_with('nonexistent-model')
|
||||
|
||||
mock_func.assert_called_once_with("nonexistent-model")
|
||||
|
||||
def test_get_openai_client_and_model(self):
|
||||
"""Test getting OpenAI client and model name"""
|
||||
test_client = MagicMock()
|
||||
default_model = "adamo1139/Hermes-3-Llama-3.1-8B-FP8-Dynamic"
|
||||
|
||||
with patch.object(app, 'get_openai_client_and_model', return_value=(test_client, default_model)) as mock_func:
|
||||
|
||||
with patch.object(
|
||||
app,
|
||||
"get_openai_client_and_model",
|
||||
return_value=(test_client, default_model),
|
||||
) as mock_func:
|
||||
client, model = app.get_openai_client_and_model()
|
||||
|
||||
|
||||
self.assertEqual(client, test_client)
|
||||
self.assertEqual(model, default_model)
|
||||
mock_func.assert_called_once()
|
||||
|
||||
|
||||
# Test with custom model
|
||||
custom_model = "gpt-4"
|
||||
with patch.object(app, 'get_openai_client_and_model', return_value=(test_client, custom_model)) as mock_func:
|
||||
with patch.object(
|
||||
app, "get_openai_client_and_model", return_value=(test_client, custom_model)
|
||||
) as mock_func:
|
||||
client, model = app.get_openai_client_and_model(custom_model)
|
||||
|
||||
|
||||
self.assertEqual(client, test_client)
|
||||
self.assertEqual(model, custom_model)
|
||||
mock_func.assert_called_once_with(custom_model)
|
||||
|
|
@ -94,21 +107,21 @@ class TestAppUtilityFunctions(unittest.TestCase):
|
|||
|
||||
class TestActivityProcessing(unittest.TestCase):
|
||||
"""Test activity processing functions"""
|
||||
|
||||
|
||||
def test_execute_processing_script_basic(self):
|
||||
"""Test basic script execution"""
|
||||
script = """
|
||||
metadata['test_key'] = 'test_value'
|
||||
script_result = {'status': 'success', 'data': 42}
|
||||
"""
|
||||
metadata = {'existing_key': 'existing_value'}
|
||||
|
||||
metadata = {"existing_key": "existing_value"}
|
||||
|
||||
result = app.execute_processing_script(metadata, script)
|
||||
|
||||
self.assertEqual(result['status'], 'success')
|
||||
self.assertEqual(result['data'], 42)
|
||||
self.assertEqual(metadata['test_key'], 'test_value')
|
||||
|
||||
|
||||
self.assertEqual(result["status"], "success")
|
||||
self.assertEqual(result["data"], 42)
|
||||
self.assertEqual(metadata["test_key"], "test_value")
|
||||
|
||||
def test_execute_processing_script_with_metadata_operations(self):
|
||||
"""Test script execution with metadata operations"""
|
||||
script = """
|
||||
|
|
@ -123,15 +136,15 @@ script_result = {
|
|||
}
|
||||
}
|
||||
"""
|
||||
metadata = {'input_value': 21, 'list_field': [1, 2, 3, 4, 5]}
|
||||
|
||||
metadata = {"input_value": 21, "list_field": [1, 2, 3, 4, 5]}
|
||||
|
||||
result = app.execute_processing_script(metadata, script)
|
||||
|
||||
self.assertEqual(metadata['new_field'], 42)
|
||||
self.assertEqual(metadata['calculated'], 5)
|
||||
self.assertTrue(result['metadata']['processed'])
|
||||
self.assertEqual(result['metadata']['calculation_result'], 42)
|
||||
|
||||
|
||||
self.assertEqual(metadata["new_field"], 42)
|
||||
self.assertEqual(metadata["calculated"], 5)
|
||||
self.assertTrue(result["metadata"]["processed"])
|
||||
self.assertEqual(result["metadata"]["calculation_result"], 42)
|
||||
|
||||
def test_execute_processing_script_with_imports(self):
|
||||
"""Test script execution with imports"""
|
||||
script = """
|
||||
|
|
@ -148,17 +161,17 @@ script_result = {
|
|||
}
|
||||
"""
|
||||
metadata = {}
|
||||
|
||||
|
||||
result = app.execute_processing_script(metadata, script)
|
||||
|
||||
self.assertTrue(result['has_random'])
|
||||
self.assertIsInstance(result['json_output'], str)
|
||||
|
||||
|
||||
self.assertTrue(result["has_random"])
|
||||
self.assertIsInstance(result["json_output"], str)
|
||||
|
||||
# Parse the JSON to verify structure
|
||||
parsed_data = json.loads(result['json_output'])
|
||||
self.assertIn('random_num', parsed_data)
|
||||
self.assertIsInstance(parsed_data['random_num'], int)
|
||||
|
||||
parsed_data = json.loads(result["json_output"])
|
||||
self.assertIn("random_num", parsed_data)
|
||||
self.assertIsInstance(parsed_data["random_num"], int)
|
||||
|
||||
def test_get_activity_content_local(self):
|
||||
"""Test loading activity content from local file"""
|
||||
test_yaml_content = """
|
||||
|
|
@ -172,70 +185,69 @@ sections:
|
|||
content_blocks:
|
||||
- "Test content"
|
||||
"""
|
||||
|
||||
with tempfile.NamedTemporaryFile(mode='w', suffix='.yaml', delete=False) as f:
|
||||
|
||||
with tempfile.NamedTemporaryFile(mode="w", suffix=".yaml", delete=False) as f:
|
||||
f.write(test_yaml_content)
|
||||
temp_file = f.name
|
||||
|
||||
|
||||
try:
|
||||
# Create a fake research directory and file
|
||||
research_dir = Path("research")
|
||||
research_dir.mkdir(exist_ok=True)
|
||||
|
||||
|
||||
test_file_path = research_dir / "test_activity.yaml"
|
||||
with open(test_file_path, 'w') as f:
|
||||
with open(test_file_path, "w") as f:
|
||||
f.write(test_yaml_content)
|
||||
|
||||
|
||||
# Set LOCAL_ACTIVITIES to True
|
||||
with patch.dict(app.app.config, {'LOCAL_ACTIVITIES': True}):
|
||||
with patch.dict(app.app.config, {"LOCAL_ACTIVITIES": True}):
|
||||
result = app.get_activity_content("research/test_activity.yaml")
|
||||
|
||||
self.assertEqual(result['default_max_attempts_per_step'], 3)
|
||||
self.assertEqual(len(result['sections']), 1)
|
||||
self.assertEqual(result['sections'][0]['section_id'], "test_section")
|
||||
|
||||
|
||||
self.assertEqual(result["default_max_attempts_per_step"], 3)
|
||||
self.assertEqual(len(result["sections"]), 1)
|
||||
self.assertEqual(result["sections"][0]["section_id"], "test_section")
|
||||
|
||||
finally:
|
||||
os.unlink(temp_file)
|
||||
if test_file_path.exists():
|
||||
test_file_path.unlink()
|
||||
|
||||
|
||||
def test_get_activity_content_local_security(self):
|
||||
"""Test that local file loading prevents path traversal"""
|
||||
with patch.dict(app.app.config, {'LOCAL_ACTIVITIES': True}):
|
||||
with patch.dict(app.app.config, {"LOCAL_ACTIVITIES": True}):
|
||||
# Test various path traversal attempts
|
||||
dangerous_paths = [
|
||||
"../etc/passwd",
|
||||
"/etc/passwd",
|
||||
"research/../../../etc/passwd",
|
||||
"research/activity.yaml../../etc/passwd"
|
||||
"research/activity.yaml../../etc/passwd",
|
||||
]
|
||||
|
||||
|
||||
for path in dangerous_paths:
|
||||
with self.assertRaises(ValueError):
|
||||
app.get_activity_content(path)
|
||||
|
||||
|
||||
def test_get_activity_content_s3(self):
|
||||
"""Test loading activity content from S3"""
|
||||
test_yaml_content = {
|
||||
'default_max_attempts_per_step': 5,
|
||||
'sections': [{
|
||||
'section_id': 's3_section',
|
||||
'title': 'S3 Section'
|
||||
}]
|
||||
"default_max_attempts_per_step": 5,
|
||||
"sections": [{"section_id": "s3_section", "title": "S3 Section"}],
|
||||
}
|
||||
|
||||
with patch.dict(app.app.config, {'LOCAL_ACTIVITIES': False}):
|
||||
with patch.object(app, 'get_activity_content', return_value=test_yaml_content) as mock_func:
|
||||
|
||||
with patch.dict(app.app.config, {"LOCAL_ACTIVITIES": False}):
|
||||
with patch.object(
|
||||
app, "get_activity_content", return_value=test_yaml_content
|
||||
) as mock_func:
|
||||
result = app.get_activity_content("path/to/activity.yaml")
|
||||
|
||||
self.assertEqual(result['default_max_attempts_per_step'], 5)
|
||||
self.assertEqual(result['sections'][0]['section_id'], "s3_section")
|
||||
|
||||
self.assertEqual(result["default_max_attempts_per_step"], 5)
|
||||
self.assertEqual(result["sections"][0]["section_id"], "s3_section")
|
||||
mock_func.assert_called_once_with("path/to/activity.yaml")
|
||||
|
||||
|
||||
class TestActivityNavigation(unittest.TestCase):
|
||||
"""Test activity navigation functions"""
|
||||
|
||||
|
||||
def setUp(self):
|
||||
"""Set up test activity content"""
|
||||
self.activity_content = {
|
||||
|
|
@ -245,115 +257,123 @@ class TestActivityNavigation(unittest.TestCase):
|
|||
"steps": [
|
||||
{"step_id": "step_1", "title": "Step 1"},
|
||||
{"step_id": "step_2", "title": "Step 2"},
|
||||
{"step_id": "step_3", "title": "Step 3"}
|
||||
]
|
||||
{"step_id": "step_3", "title": "Step 3"},
|
||||
],
|
||||
},
|
||||
{
|
||||
"section_id": "section_2",
|
||||
"section_id": "section_2",
|
||||
"steps": [
|
||||
{"step_id": "step_1", "title": "Section 2 Step 1"},
|
||||
{"step_id": "step_2", "title": "Section 2 Step 2"}
|
||||
]
|
||||
}
|
||||
{"step_id": "step_2", "title": "Section 2 Step 2"},
|
||||
],
|
||||
},
|
||||
]
|
||||
}
|
||||
|
||||
|
||||
def test_get_next_step_within_section(self):
|
||||
"""Test getting next step within the same section"""
|
||||
next_section, next_step = app.get_next_step(
|
||||
self.activity_content, "section_1", "step_1"
|
||||
)
|
||||
|
||||
|
||||
self.assertEqual(next_section["section_id"], "section_1")
|
||||
self.assertEqual(next_step["step_id"], "step_2")
|
||||
|
||||
|
||||
def test_get_next_step_across_sections(self):
|
||||
"""Test getting next step across sections"""
|
||||
next_section, next_step = app.get_next_step(
|
||||
self.activity_content, "section_1", "step_3"
|
||||
)
|
||||
|
||||
|
||||
self.assertEqual(next_section["section_id"], "section_2")
|
||||
self.assertEqual(next_step["step_id"], "step_1")
|
||||
|
||||
|
||||
def test_get_next_step_at_end(self):
|
||||
"""Test getting next step when at the end of activity"""
|
||||
next_section, next_step = app.get_next_step(
|
||||
self.activity_content, "section_2", "step_2"
|
||||
)
|
||||
|
||||
|
||||
self.assertIsNone(next_section)
|
||||
self.assertIsNone(next_step)
|
||||
|
||||
|
||||
def test_get_next_step_invalid_section(self):
|
||||
"""Test getting next step with invalid section"""
|
||||
next_section, next_step = app.get_next_step(
|
||||
self.activity_content, "invalid_section", "step_1"
|
||||
)
|
||||
|
||||
|
||||
self.assertIsNone(next_section)
|
||||
self.assertIsNone(next_step)
|
||||
|
||||
|
||||
def test_get_next_step_invalid_step(self):
|
||||
"""Test getting next step with invalid step"""
|
||||
next_section, next_step = app.get_next_step(
|
||||
self.activity_content, "section_1", "invalid_step"
|
||||
)
|
||||
|
||||
|
||||
self.assertIsNone(next_section)
|
||||
self.assertIsNone(next_step)
|
||||
|
||||
|
||||
class TestResponseCategorizationAndFeedback(unittest.TestCase):
|
||||
"""Test response categorization and feedback generation"""
|
||||
|
||||
|
||||
def test_categorize_response_simple_format(self):
|
||||
"""Test response categorization with simple format"""
|
||||
with patch.object(app, 'categorize_response', return_value="correct") as mock_func:
|
||||
result = app.categorize_response(
|
||||
"What is 2+2?",
|
||||
"4",
|
||||
["correct", "incorrect"],
|
||||
"Categorize as correct or incorrect"
|
||||
)
|
||||
|
||||
self.assertEqual(result, "correct")
|
||||
mock_func.assert_called_once_with(
|
||||
"What is 2+2?",
|
||||
"4",
|
||||
["correct", "incorrect"],
|
||||
"Categorize as correct or incorrect"
|
||||
)
|
||||
|
||||
def test_categorize_response_analysis_bucket_format(self):
|
||||
"""Test response categorization with ANALYSIS/BUCKET format"""
|
||||
with patch.object(app, 'categorize_response', return_value="correct") as mock_func:
|
||||
with patch.object(
|
||||
app, "categorize_response", return_value="correct"
|
||||
) as mock_func:
|
||||
result = app.categorize_response(
|
||||
"What is 2+2?",
|
||||
"4",
|
||||
["correct", "incorrect"],
|
||||
"ANALYSIS: Analyze the response. BUCKET: Choose correct or incorrect."
|
||||
["correct", "incorrect"],
|
||||
"Categorize as correct or incorrect",
|
||||
)
|
||||
|
||||
|
||||
self.assertEqual(result, "correct")
|
||||
mock_func.assert_called_once_with(
|
||||
"What is 2+2?",
|
||||
"4",
|
||||
["correct", "incorrect"],
|
||||
"Categorize as correct or incorrect",
|
||||
)
|
||||
|
||||
def test_categorize_response_analysis_bucket_format(self):
|
||||
"""Test response categorization with ANALYSIS/BUCKET format"""
|
||||
with patch.object(
|
||||
app, "categorize_response", return_value="correct"
|
||||
) as mock_func:
|
||||
result = app.categorize_response(
|
||||
"What is 2+2?",
|
||||
"4",
|
||||
["correct", "incorrect"],
|
||||
"ANALYSIS: Analyze the response. BUCKET: Choose correct or incorrect.",
|
||||
)
|
||||
|
||||
self.assertEqual(result, "correct")
|
||||
mock_func.assert_called_once()
|
||||
|
||||
|
||||
def test_categorize_response_with_spaces_and_case(self):
|
||||
"""Test response categorization handles spaces and case properly"""
|
||||
with patch.object(app, 'categorize_response', return_value="partially_correct") as mock_func:
|
||||
with patch.object(
|
||||
app, "categorize_response", return_value="partially_correct"
|
||||
) as mock_func:
|
||||
result = app.categorize_response(
|
||||
"Test question",
|
||||
"Test response",
|
||||
["partially_correct", "incorrect"],
|
||||
"Categorize the response"
|
||||
"Categorize the response",
|
||||
)
|
||||
|
||||
|
||||
self.assertEqual(result, "partially_correct")
|
||||
mock_func.assert_called_once()
|
||||
|
||||
|
||||
def test_generate_ai_feedback(self):
|
||||
"""Test AI feedback generation"""
|
||||
with patch.object(app, 'generate_ai_feedback', return_value="Great job! You got it right.") as mock_func:
|
||||
with patch.object(
|
||||
app, "generate_ai_feedback", return_value="Great job! You got it right."
|
||||
) as mock_func:
|
||||
result = app.generate_ai_feedback(
|
||||
"correct",
|
||||
"What is 2+2?",
|
||||
|
|
@ -361,112 +381,114 @@ class TestResponseCategorizationAndFeedback(unittest.TestCase):
|
|||
"Provide encouraging feedback",
|
||||
"testuser",
|
||||
"{}",
|
||||
"{}"
|
||||
"{}",
|
||||
)
|
||||
|
||||
|
||||
self.assertEqual(result, "Great job! You got it right.")
|
||||
mock_func.assert_called_once()
|
||||
|
||||
|
||||
def test_provide_feedback_with_ai_feedback(self):
|
||||
"""Test provide_feedback function with AI feedback"""
|
||||
transition = {
|
||||
"ai_feedback": {
|
||||
"tokens_for_ai": "Be encouraging"
|
||||
}
|
||||
}
|
||||
|
||||
with patch.object(app, 'provide_feedback', return_value="Excellent work!") as mock_func:
|
||||
transition = {"ai_feedback": {"tokens_for_ai": "Be encouraging"}}
|
||||
|
||||
with patch.object(
|
||||
app, "provide_feedback", return_value="Excellent work!"
|
||||
) as mock_func:
|
||||
result = app.provide_feedback(
|
||||
transition,
|
||||
"correct",
|
||||
"correct",
|
||||
"Test question",
|
||||
"Base instructions",
|
||||
"Test response",
|
||||
"English",
|
||||
"testuser",
|
||||
"{}",
|
||||
"{}"
|
||||
"{}",
|
||||
)
|
||||
|
||||
|
||||
self.assertEqual(result, "Excellent work!")
|
||||
mock_func.assert_called_once()
|
||||
|
||||
|
||||
def test_provide_feedback_without_ai_feedback(self):
|
||||
"""Test provide_feedback function without AI feedback"""
|
||||
transition = {}
|
||||
|
||||
|
||||
result = app.provide_feedback(
|
||||
transition,
|
||||
"correct",
|
||||
"Test question",
|
||||
"Test question",
|
||||
"Base instructions",
|
||||
"Test response",
|
||||
"English",
|
||||
"testuser",
|
||||
"{}",
|
||||
"{}"
|
||||
"{}",
|
||||
)
|
||||
|
||||
|
||||
self.assertEqual(result, "")
|
||||
|
||||
|
||||
class TestTranslationAndLanguage(unittest.TestCase):
|
||||
"""Test translation and language handling"""
|
||||
|
||||
|
||||
def test_translate_text_english_bypass(self):
|
||||
"""Test that English text is not translated"""
|
||||
text = "Hello, world!"
|
||||
result = app.translate_text(text, "English")
|
||||
self.assertEqual(result, text)
|
||||
|
||||
|
||||
# Test case insensitive
|
||||
result = app.translate_text(text, "english")
|
||||
result = app.translate_text(text, "english")
|
||||
self.assertEqual(result, text)
|
||||
|
||||
|
||||
# Test with compound language specification
|
||||
result = app.translate_text(text, "english please")
|
||||
self.assertEqual(result, text)
|
||||
|
||||
|
||||
def test_translate_text_other_language(self):
|
||||
"""Test translation to other languages"""
|
||||
with patch.object(app, 'translate_text', return_value="Hola, mundo!") as mock_func:
|
||||
with patch.object(
|
||||
app, "translate_text", return_value="Hola, mundo!"
|
||||
) as mock_func:
|
||||
result = app.translate_text("Hello, world!", "Spanish")
|
||||
|
||||
|
||||
self.assertEqual(result, "Hola, mundo!")
|
||||
mock_func.assert_called_once_with("Hello, world!", "Spanish")
|
||||
|
||||
|
||||
def test_translate_text_error_handling(self):
|
||||
"""Test translation error handling"""
|
||||
with patch.object(app, 'translate_text', return_value="Error: Translation failed") as mock_func:
|
||||
with patch.object(
|
||||
app, "translate_text", return_value="Error: Translation failed"
|
||||
) as mock_func:
|
||||
result = app.translate_text("Hello, world!", "Spanish")
|
||||
|
||||
|
||||
self.assertIn("Error:", result)
|
||||
mock_func.assert_called_once_with("Hello, world!", "Spanish")
|
||||
|
||||
|
||||
class TestS3Operations(unittest.TestCase):
|
||||
"""Test S3 related functions"""
|
||||
|
||||
|
||||
def test_get_s3_client_with_profile(self):
|
||||
"""Test S3 client creation with profile"""
|
||||
mock_client = MagicMock()
|
||||
|
||||
with patch.object(app, 'get_s3_client', return_value=mock_client) as mock_func:
|
||||
|
||||
with patch.object(app, "get_s3_client", return_value=mock_client) as mock_func:
|
||||
result = app.get_s3_client()
|
||||
|
||||
|
||||
self.assertEqual(result, mock_client)
|
||||
mock_func.assert_called_once()
|
||||
|
||||
|
||||
def test_get_s3_client_without_profile(self):
|
||||
"""Test S3 client creation without profile"""
|
||||
mock_client = MagicMock()
|
||||
|
||||
with patch.object(app, 'get_s3_client', return_value=mock_client) as mock_func:
|
||||
|
||||
with patch.object(app, "get_s3_client", return_value=mock_client) as mock_func:
|
||||
result = app.get_s3_client()
|
||||
|
||||
|
||||
self.assertEqual(result, mock_client)
|
||||
mock_func.assert_called_once()
|
||||
|
||||
|
||||
def test_find_most_recent_code_block(self):
|
||||
"""Test finding most recent code block in messages"""
|
||||
# This would require mocking the database and Message model
|
||||
|
|
@ -480,14 +502,14 @@ def test_function():
|
|||
|
||||
And some more text after.
|
||||
"""
|
||||
|
||||
|
||||
# Extract the code block manually to test the logic
|
||||
lines = test_content.split('\n')
|
||||
lines = test_content.split("\n")
|
||||
code_block_lines = []
|
||||
code_block_started = False
|
||||
|
||||
|
||||
for line in lines:
|
||||
if line.startswith('```'):
|
||||
if line.startswith("```"):
|
||||
if code_block_started:
|
||||
break
|
||||
else:
|
||||
|
|
@ -495,17 +517,17 @@ And some more text after.
|
|||
continue
|
||||
elif code_block_started:
|
||||
code_block_lines.append(line)
|
||||
|
||||
result = '\n'.join(code_block_lines)
|
||||
|
||||
result = "\n".join(code_block_lines)
|
||||
expected = """def test_function():
|
||||
return "Hello, World!\""""
|
||||
|
||||
|
||||
self.assertEqual(result, expected)
|
||||
|
||||
|
||||
class TestUtilityFunctions(unittest.TestCase):
|
||||
"""Test various utility functions"""
|
||||
|
||||
|
||||
def test_group_consecutive_roles(self):
|
||||
"""Test grouping consecutive roles in messages"""
|
||||
messages = [
|
||||
|
|
@ -513,24 +535,24 @@ class TestUtilityFunctions(unittest.TestCase):
|
|||
{"role": "user", "content": "How are you?"},
|
||||
{"role": "assistant", "content": "I'm fine"},
|
||||
{"role": "assistant", "content": "Thanks for asking"},
|
||||
{"role": "user", "content": "Great!"}
|
||||
{"role": "user", "content": "Great!"},
|
||||
]
|
||||
|
||||
|
||||
result = app.group_consecutive_roles(messages)
|
||||
|
||||
|
||||
expected = [
|
||||
{"role": "user", "content": "Hello How are you?"},
|
||||
{"role": "assistant", "content": "I'm fine Thanks for asking"},
|
||||
{"role": "user", "content": "Great!"}
|
||||
{"role": "user", "content": "Great!"},
|
||||
]
|
||||
|
||||
|
||||
self.assertEqual(result, expected)
|
||||
|
||||
|
||||
def test_group_consecutive_roles_empty(self):
|
||||
"""Test grouping consecutive roles with empty input"""
|
||||
result = app.group_consecutive_roles([])
|
||||
self.assertEqual(result, [])
|
||||
|
||||
|
||||
def test_group_consecutive_roles_single(self):
|
||||
"""Test grouping consecutive roles with single message"""
|
||||
messages = [{"role": "user", "content": "Hello"}]
|
||||
|
|
@ -538,5 +560,5 @@ class TestUtilityFunctions(unittest.TestCase):
|
|||
self.assertEqual(result, messages)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main(verbosity=2)
|
||||
if __name__ == "__main__":
|
||||
unittest.main(verbosity=2)
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue