- Add UIXT runner with MCP plugin support
- Refactor AI service options handling
- Optimize configuration parsing for LLM and CV services
- Update dependencies to latest versions
- Add complete LianLianKan game bot with AI-powered interface analysis
- Implement static analysis solver with 0-2 turn connection algorithms
- Support cross-platform game automation (Android, iOS, HarmonyOS, Browser)
- Include comprehensive test suite with real game data
- Add command line tool and documentation
- Integrate with HttpRunner @/uixt module and Doubao AI models
- Add LLMServiceConfig to support mixed model configuration
- Enable Planner, Asserter, Querier to use different optimal models
- Provide recommended configurations for various use cases
- Maintain backward compatibility with existing API
- Update documentation to reflect current state without iteration history
- Merge test files and add comprehensive configuration tests
- Resolve circular dependency by moving config to option package
- Add comprehensive documentation for the new Query functionality
- Update interface method names from Call to Plan for consistency
- Add OpenAI GPT-4O model support documentation
- Include detailed usage examples for basic and custom schema queries
- Add configuration examples for multiple model services
- Document new features like ResetHistory, Usage statistics, and automatic type conversion
- Expand advanced features section with custom output format examples
- Update all code examples to reflect the latest API changes
The documentation now reflects the current state of the AI module with all three core capabilities:
- Planning (renamed from Call)
- Assertion
- Query (new feature)
All examples and configurations are updated to match the latest implementation.
- Add Query method to ILLMService interface for unified AI service access
- Update combinedLLMService to include querier functionality
- Add comprehensive tests for ILLMService Query method
- Support both basic query and custom schema query through unified interface
- Add environment variable checks for test reliability
This allows users to access all AI capabilities (planning, assertion, and query)
through a single ILLMService interface, providing better API consistency and ease of use.
- Add new AI Querier module for structured information extraction from screenshots
- Support custom output schema for structured data response
- Implement automatic type conversion and data validation
- Add comprehensive test suite with various data structure examples
- Refactor callModelWithLogging to utils.go as shared function for planner, asserter, and querier
- Eliminate code duplication across AI modules (30+ lines of repeated code)
- Improve maintainability with unified logging and timing logic
- Add environment variable checks in test setup to handle missing API keys gracefully
Key features:
- Custom output schema support with JSON Schema generation
- Automatic data type conversion with reflection
- Fallback mechanisms for robust parsing
- Comprehensive documentation and usage examples
- Backward compatibility with existing functionality
- Add decodeBase64UTF8 function to properly handle UTF-8 encoded Base64 content
- Replace atob() with TextDecoder for correct Chinese character decoding
- Explicitly specify UTF-8 charset when creating download Blob
- Fix garbled Chinese text when downloading summary.json from HTML report
- Handle direction parameter in convertProcessedArgs for scroll actions
- Ensure scroll operations map to swipe with both coordinates and direction
- Add comprehensive test coverage for scroll action parsing
- Fix issue where scroll direction was missing from tool call arguments
- Replace byte-based brace counting with UTF-8 aware rune iteration
- Add proper string state tracking to handle escaped quotes
- Add comprehensive test cases for Chinese character handling
- Fix parsing errors when JSON contains Chinese text like 2048经典
- Fix JSON extraction logic by prioritizing brace counting method
- Add support for DOUBAO string array coordinate format
- Introduce IS_UI_TARS helper function for model type checking
- Add comprehensive tests for JSON parsing and coordinate handling
- Improve error handling with retry delays for LLM service failures
- Implement lazy loading for directory creation in config.go
- Add logFile parameter to InitLogger for better control
- Use dynamic directory existence check instead of flags
- Report command now uses console-only logging to prevent directory creation
- Support both JSON and colorized console output formats
- Maintain backward compatibility for all other commands
Changes:
- config.go: Convert directory paths to getter methods with lazy creation
- logger.go: Add logFile parameter and improve logging control
- cmd/root.go: Detect report command and disable file logging
- uixt/*: Update all references to use new getter methods
Fixes the issue where 'hrp report results/' would create unwanted timestamp directories
- Add RegisterTools method to ILLMService interface
- Create shared MCP to eino tool converter
- Auto-register built-in uixt tools in XTDriver initialization
- Refactor MCPHost to use shared converter
- Add comprehensive test coverage for tool conversion
This enables doubao-1.5-thinking-vision-pro model to access
MCP tools through function calling mechanism.
- Console logger respects user-specified log level
- File logger always uses DEBUG level to capture all logs
- Add custom leveledMultiWriter for different output levels
- Remove global log level setting for more granular control
- Add ModelName field to PlanningResult and SubActionResult
- Update HTML report with improved layout and model name display
- Fix elapsed time setting bug and enhance mobile responsiveness
- Move log message to same line as timestamp and level
- Reduce padding and font sizes for tighter spacing
- Optimize log data display with left border and indentation
- Add responsive design for mobile devices
- Achieve more compact display with fewer lines per log entry
- Fix JSON serialization to preserve Chinese characters instead of Unicode escaping
- Use SetEscapeHTML(false) in toJSON template function
- Apply safeHTML to prevent HTML entity encoding of Chinese text
- Now displays {"text":"连了又连"} instead of {"text":"连了又连"}
- Add complete HTML report generator with template-based rendering
- Implement log time filtering for step-specific logs
- Support responsive design and interactive UI features
- Consolidate duplicate report implementations
- Use defer for summary saving and HTML report generation to ensure they run regardless of exit path
- Remove unnecessary sync.Once for cleanup operations since defer guarantees single execution
- Simplify error handling logic by removing redundant runErr checks
- Improve interrupt handling with better logging messages
- Ensure graceful cleanup and data persistence even when interrupted
- Fix parameter mapping issue where AI model's 'content' parameter wasn't mapped to 'text' field
- Add mapParameterName function to handle parameter name mapping (content->text, key->keycode)
- Add comprehensive unit tests for convertProcessedArgs and mapParameterName functions
- Update existing test cases to match new parameter format (x,y for single coords, from_x,from_y,to_x,to_y for drag)
This resolves the issue where uixt__input action was not working due to parameter name mismatch.
- Support configuring multiple LLM services simultaneously
- Auto-derive model names from service types to simplify configuration
- Maintain backward compatibility with existing configurations
- Refactor configuration logic into dedicated env module
- Add comprehensive unit test coverage
- Update documentation with new configuration approach
- Add ResetHistory option to PlanningOptions and ActionOptions
- Implement task completion detection with isTaskFinished() method
- Add executeActions() method to separate action execution logic
- Modify ConversationHistory.Clear() to completely clear all messages including system message
- Refactor StartToGoal() to automatically reset history on first attempt
- Add WithResetHistory() option function for consistent API
- Consolidate test files into driver_ext_ai_test.go with comprehensive test coverage
- Remove all manual ReturnSchema() methods from tools
- Implement automatic schema generation using reflection
- Unify response format to flat structure with action/success/message fields
- Simplify tool implementation by removing MCPResponse embedding
- Update documentation to reflect new architecture
- Achieve ~70% code reduction while maintaining type safety
