101 lines
5.8 KiB
Plaintext
101 lines
5.8 KiB
Plaintext
# Task ID: 24
|
|
# Title: Implement AI-Powered Test Generation Command
|
|
# Status: pending
|
|
# Dependencies: 22
|
|
# Priority: high
|
|
# Description: Create a new 'generate-test' command in Task Master that leverages AI to automatically produce Jest test files for tasks based on their descriptions and subtasks, utilizing Claude API for AI integration.
|
|
# Details:
|
|
Implement a new command in the Task Master CLI that generates comprehensive Jest test files for tasks. The command should be callable as 'task-master generate-test --id=1' and should:
|
|
|
|
1. Accept a task ID parameter to identify which task to generate tests for
|
|
2. Retrieve the task and its subtasks from the task store
|
|
3. Analyze the task description, details, and subtasks to understand implementation requirements
|
|
4. Construct an appropriate prompt for the AI service using Claude API
|
|
5. Process the AI response to create a well-formatted test file named 'task_XXX.test.ts' where XXX is the zero-padded task ID
|
|
6. Include appropriate test cases that cover the main functionality described in the task
|
|
7. Generate mocks for external dependencies identified in the task description
|
|
8. Create assertions that validate the expected behavior
|
|
9. Handle both parent tasks and subtasks appropriately (for subtasks, name the file 'task_XXX_YYY.test.ts' where YYY is the subtask ID)
|
|
10. Include error handling for API failures, invalid task IDs, etc.
|
|
11. Add appropriate documentation for the command in the help system
|
|
|
|
The implementation should utilize the Claude API for AI service integration and maintain consistency with the current command structure and error handling patterns. Consider using TypeScript for better type safety and integration with the Claude API.
|
|
|
|
# Test Strategy:
|
|
Testing for this feature should include:
|
|
|
|
1. Unit tests for the command handler function to verify it correctly processes arguments and options
|
|
2. Mock tests for the Claude API integration to ensure proper prompt construction and response handling
|
|
3. Integration tests that verify the end-to-end flow using a mock Claude API response
|
|
4. Tests for error conditions including:
|
|
- Invalid task IDs
|
|
- Network failures when contacting the AI service
|
|
- Malformed AI responses
|
|
- File system permission issues
|
|
5. Verification that generated test files follow Jest conventions and can be executed
|
|
6. Tests for both parent task and subtask handling
|
|
7. Manual verification of the quality of generated tests by running them against actual task implementations
|
|
|
|
Create a test fixture with sample tasks of varying complexity to evaluate the test generation capabilities across different scenarios. The tests should verify that the command outputs appropriate success/error messages to the console and creates files in the expected location with proper content structure.
|
|
|
|
# Subtasks:
|
|
## 1. Create command structure for 'generate-test' [pending]
|
|
### Dependencies: None
|
|
### Description: Implement the basic structure for the 'generate-test' command, including command registration, parameter validation, and help documentation.
|
|
### Details:
|
|
Implementation steps:
|
|
1. Create a new file `src/commands/generate-test.ts`
|
|
2. Implement the command structure following the pattern of existing commands
|
|
3. Register the new command in the CLI framework
|
|
4. Add command options for task ID (--id=X) parameter
|
|
5. Implement parameter validation to ensure a valid task ID is provided
|
|
6. Add help documentation for the command
|
|
7. Create the basic command flow that retrieves the task from the task store
|
|
8. Implement error handling for invalid task IDs and other basic errors
|
|
|
|
Testing approach:
|
|
- Test command registration
|
|
- Test parameter validation (missing ID, invalid ID format)
|
|
- Test error handling for non-existent task IDs
|
|
- Test basic command flow with a mock task store
|
|
|
|
## 2. Implement AI prompt construction [pending]
|
|
### Dependencies: 24.1
|
|
### Description: Develop the logic to analyze tasks, construct appropriate AI prompts, and interact with the AI service using the existing ai-service.js to generate test content.
|
|
### Details:
|
|
Implementation steps:
|
|
1. Create a utility function to analyze task descriptions and subtasks for test requirements
|
|
2. Implement a prompt builder that formats task information into an effective AI prompt
|
|
3. Use ai-service.js as needed to send the prompt and receive the response (streaming)
|
|
4. Process the response to extract the generated test code
|
|
5. Implement error handling for failures, rate limits, and malformed responses
|
|
6. Add appropriate logging for the test generation process
|
|
|
|
Testing approach:
|
|
- Test prompt construction with various task types
|
|
- Test ai services integration with mocked responses
|
|
- Test error handling for ai service failures
|
|
- Test response processing with sample ai-services.js outputs
|
|
|
|
## 3. Implement test file generation and output [pending]
|
|
### Dependencies: 24.2
|
|
### Description: Create functionality to format AI-generated tests into proper Jest test files and save them to the appropriate location.
|
|
### Details:
|
|
Implementation steps:
|
|
1. Create a utility to format the ai-services.js response into a well-structured Jest test file
|
|
2. Implement naming logic for test files (task_XXX.test.ts for parent tasks, task_XXX_YYY.test.ts for subtasks)
|
|
3. Add logic to determine the appropriate file path for saving the test
|
|
4. Implement file system operations to write the test file
|
|
5. Add validation to ensure the generated test follows Jest conventions
|
|
6. Implement formatting of the test file for consistency with project coding standards
|
|
7. Add user feedback about successful test generation and file location
|
|
8. Implement handling for both parent tasks and subtasks
|
|
|
|
Testing approach:
|
|
- Test file naming logic for various task/subtask combinations
|
|
- Test file content formatting with sample ai-services.js outputs
|
|
- Test file system operations with mocked fs module
|
|
- Test the complete flow from command input to file output
|
|
- Verify generated tests can be executed by Jest
|
|
|