c5738a2513
This commit introduces a comprehensive set of skipped tests to both and . These skipped tests serve as a blueprint for future test implementation, outlining the necessary test cases for currently untested functionalities.
- Ensures sync with bin/ folder by adding -r/--research to the command
- Fixes an issue that improperly parsed command line args
- Ensures confirmation card on dependency add/remove
- Properly formats some sub-task dependencies
**Potentially addressed issues:**
While primarily focused on adding test coverage, this commit also implicitly addresses potential issues by:
- **Improving error handling coverage:** The addition of skipped tests for error scenarios in functions like , , , and highlights areas where error handling needs to be robustly tested and potentially improved in the codebase.
- **Enhancing dependency validation:** Skipped tests for include validation of dependencies, prompting a review of the dependency validation logic and ensuring its correctness.
- **Standardizing test coverage:** By creating a clear roadmap for testing all functions, this commit contributes to a more standardized and complete test suite, reducing the likelihood of undiscovered bugs in the future.
**task-manager.test.js:**
- Added skipped test blocks for the following functions:
- : Includes tests for handling valid JSON responses, malformed JSON, missing tasks in responses, Perplexity AI research integration, Claude fallback, and parallel task processing.
- : Covers tests for updating tasks based on context, handling Claude streaming, Perplexity AI integration, scenarios with no tasks to update, and error handling during updates.
- : Includes tests for generating task files from , formatting dependencies with status indicators, handling tasks without subtasks, empty task arrays, and dependency validation before file generation.
- : Covers tests for updating task status, subtask status using dot notation, updating multiple tasks, automatic subtask status updates, parent task update suggestions, and handling non-existent task IDs.
- : Includes tests for updating regular and subtask statuses, handling parent tasks without subtasks, and non-existent subtask IDs.
- : Covers tests for displaying all tasks, filtering by status, displaying subtasks, showing completion statistics, identifying the next task, and handling empty task arrays.
- : Includes tests for generating subtasks, using complexity reports for subtask counts, Perplexity AI integration, appending subtasks, skipping completed tasks, and error handling during subtask generation.
- : Covers tests for expanding all pending tasks, sorting by complexity, skipping tasks with existing subtasks (unless forced), using task-specific parameters from complexity reports, handling empty task arrays, and error handling for individual tasks.
- : Includes tests for clearing subtasks from specific and multiple tasks, handling tasks without subtasks, non-existent task IDs, and regenerating task files after clearing subtasks.
- : Covers tests for adding new tasks using AI, handling Claude streaming, validating dependencies, handling malformed AI responses, and using existing task context for generation.
**utils.test.js:**
- Added skipped test blocks for the following functions:
- : Tests for logging messages according to log levels and filtering messages below configured levels.
- : Tests for reading and parsing valid JSON files, handling file not found errors, and invalid JSON formats.
- : Tests for writing JSON data to files and handling file write errors.
- : Tests for escaping double quotes in prompts and handling prompts without special characters.
- : Tests for reading and parsing complexity reports, handling missing report files, and custom report paths.
- : Tests for finding tasks in reports by ID, handling non-existent task IDs, and invalid report structures.
- : Tests for verifying existing task and subtask IDs, handling non-existent IDs, and invalid inputs.
- : Tests for formatting numeric and string task IDs and preserving dot notation for subtasks.
- : Tests for detecting simple and complex cycles in dependency graphs, handling acyclic graphs, and empty dependency maps.
These skipped tests provide a clear roadmap for future test development, ensuring comprehensive coverage for core functionalities in both modules. They document the intended behavior of each function and outline various scenarios, including happy paths, edge cases, and error conditions, thereby improving the overall test strategy and maintainability of the Task Master CLI.
56 lines
3.4 KiB
Plaintext
56 lines
3.4 KiB
Plaintext
# Task ID: 5
|
|
# Title: Integrate Anthropic Claude API
|
|
# Status: done
|
|
# Dependencies: 1
|
|
# Priority: high
|
|
# Description: Set up the integration with Claude API for AI-powered task generation and expansion.
|
|
# Details:
|
|
Implement Claude API integration including:
|
|
- API authentication using environment variables
|
|
- Create prompt templates for various operations
|
|
- Implement response handling and parsing
|
|
- Add error management with retries and exponential backoff
|
|
- Implement token usage tracking
|
|
- Create configurable model parameters
|
|
|
|
# Test Strategy:
|
|
Test API connectivity with sample prompts. Verify authentication works correctly with different API keys. Test error handling by simulating API failures.
|
|
|
|
# Subtasks:
|
|
## 1. Configure API Authentication System [done]
|
|
### Dependencies: None
|
|
### Description: Create a dedicated module for Anthropic API authentication. Implement a secure system to load API keys from environment variables using dotenv. Include validation to ensure API keys are properly formatted and present. Create a configuration object that will store all Claude-related settings including API keys, base URLs, and default parameters.
|
|
### Details:
|
|
|
|
|
|
## 2. Develop Prompt Template System [done]
|
|
### Dependencies: 5.1
|
|
### Description: Create a flexible prompt template system for Claude API interactions. Implement a PromptTemplate class that can handle variable substitution, system and user messages, and proper formatting according to Claude's requirements. Include templates for different operations (task generation, task expansion, etc.) with appropriate instructions and constraints for each use case.
|
|
### Details:
|
|
|
|
|
|
## 3. Implement Response Handling and Parsing [done]
|
|
### Dependencies: 5.1, 5.2
|
|
### Description: Create a response handling system that processes Claude API responses. Implement JSON parsing for structured outputs, error detection in responses, and extraction of relevant information. Build utility functions to transform Claude's responses into the application's data structures. Include validation to ensure responses meet expected formats.
|
|
### Details:
|
|
|
|
|
|
## 4. Build Error Management with Retry Logic [done]
|
|
### Dependencies: 5.1, 5.3
|
|
### Description: Implement a robust error handling system for Claude API interactions. Create middleware that catches API errors, network issues, and timeout problems. Implement exponential backoff retry logic that increases wait time between retries. Add configurable retry limits and timeout settings. Include detailed logging for troubleshooting API issues.
|
|
### Details:
|
|
|
|
|
|
## 5. Implement Token Usage Tracking [done]
|
|
### Dependencies: 5.1, 5.3
|
|
### Description: Create a token tracking system to monitor Claude API usage. Implement functions to count tokens in prompts and responses. Build a logging system that records token usage per operation. Add reporting capabilities to show token usage trends and costs. Implement configurable limits to prevent unexpected API costs.
|
|
### Details:
|
|
|
|
|
|
## 6. Create Model Parameter Configuration System [done]
|
|
### Dependencies: 5.1, 5.5
|
|
### Description: Implement a flexible system for configuring Claude model parameters. Create a configuration module that manages model selection, temperature, top_p, max_tokens, and other parameters. Build functions to customize parameters based on operation type. Add validation to ensure parameters are within acceptable ranges. Include preset configurations for different use cases (creative, precise, etc.).
|
|
### Details:
|
|
|
|
|