3e838ed34b
Implements Claude Code as a new AI provider that uses the Claude Code CLI without requiring API keys. This enables users to leverage Claude models through their local Claude Code installation. Key changes: - Add complete AI SDK v1 implementation for Claude Code provider - Custom SDK with streaming/non-streaming support - Session management for conversation continuity - JSON extraction for object generation mode - Support for advanced settings (maxTurns, allowedTools, etc.) - Integrate Claude Code into Task Master's provider system - Update ai-services-unified.js to handle keyless authentication - Add provider to supported-models.json with opus/sonnet models - Ensure correct maxTokens values are applied (opus: 32000, sonnet: 64000) - Fix maxTokens configuration issue - Add max_tokens property to getAvailableModels() output - Update setModel() to properly handle claude-code models - Create update-config-tokens.js utility for init process - Add comprehensive documentation - User guide with configuration examples - Advanced settings explanation and future integration options The implementation maintains full backward compatibility with existing providers while adding seamless Claude Code support to all Task Master commands.
Task Master Test Suite
This directory contains tests for the Task Master CLI. The tests are organized into different categories to ensure comprehensive test coverage.
Test Structure
unit/: Unit tests for individual functions and componentsintegration/: Integration tests for testing interactions between componentse2e/: End-to-end tests for testing complete workflowsfixtures/: Test fixtures and sample data
Running Tests
To run all tests:
npm test
To run tests in watch mode (for development):
npm run test:watch
To run tests with coverage reporting:
npm run test:coverage
Testing Approach
Unit Tests
Unit tests focus on testing individual functions and components in isolation. These tests should be fast and should mock external dependencies.
Integration Tests
Integration tests focus on testing interactions between components. These tests ensure that components work together correctly.
End-to-End Tests
End-to-end tests focus on testing complete workflows from a user's perspective. These tests ensure that the CLI works correctly as a whole.
Test Fixtures
Test fixtures provide sample data for tests. Fixtures should be small, focused, and representative of real-world data.
Mocking
For external dependencies like file system operations and API calls, we use mocking to isolate the code being tested.
- File system operations: Use
mock-fsto mock the file system - API calls: Use Jest's mocking capabilities to mock API responses
Test Coverage
We aim for at least 80% test coverage for all code paths. Coverage reports can be generated with:
npm run test:coverage