- Introduced `GuiActionGenerator` class to convert high-level AI actions into executable GUI test scripts, supporting JSON output for automated testing.
- Added comprehensive test suite for AI tile placement commands, validating command parsing and generated test scripts.
- Updated `README.md` to reflect recent enhancements and completed features in the project.
- Improved CMake configuration to include new source files for GUI action generation and related services.
- Introduced `AIActionParser` class to parse natural language commands into structured GUI actions, supporting commands like placing tiles and opening editors.
- Implemented helper functions for extracting coordinates and parsing hex/decimal values.
- Added action types for various AI actions, including selecting and placing tiles, saving changes, and clicking buttons.
- Created header file `ai_action_parser.h` to define the action types and parser interface.
- Added implementation file `ai_action_parser.cc` with command parsing logic and pattern matching for different action types.
- Revised function schemas in `function_schemas.json` to streamline resource listing and searching, including new parameters for dungeon and overworld queries.
- Introduced a new system prompt in `system_prompt_v3.txt` to improve the agent's proactive exploration and multi-tool chaining strategies.
- Updated `GeminiAIService` to support the new prompt version and enhanced function calling logic for better tool integration.
- Added tests for multimodal image analysis and error handling in `test_gemini_vision.cc` to ensure robust functionality.
- Introduced the `agent learn` command to manage learned knowledge, including user preferences, ROM patterns, project context, and conversation memory.
- Added functionality for setting, getting, listing preferences, and managing project contexts.
- Implemented memory storage and retrieval, allowing the agent to remember past conversations and key facts.
- Enhanced CLI output with usage instructions and error handling for the learn command.
- Created a new `LearnedKnowledgeService` to handle persistent data storage and retrieval.
- Updated system prompt loading functionality to support both version 1 and version 2 prompts, allowing users to load built-in prompts directly.
- Implemented custom system prompt loading and saving capabilities, enabling users to manage their prompts more effectively.
- Added methods to load and save agent settings from/to project files, including AI provider configurations and custom prompts.
- Improved user feedback with toast notifications for successful and failed operations related to system prompts and settings.
- Implemented new commands for listing overworld sprites and retrieving entrance details.
- Enhanced CLI functionality to support filtering by map, world, and sprite ID with JSON and text output formats.
- Introduced tile statistics analysis command for detailed tile usage insights.
- Updated function schemas and system prompts to reflect the new commands and their parameters.
- Added functionality for listing, reading, and searching messages in the ROM.
- Introduced new commands: `message-list`, `message-read`, and `message-search` with appropriate parameters and descriptions.
- Enhanced the CLI to support these commands, including JSON and text output formats.
- Updated system prompts and function schemas to reflect the new message handling capabilities.
- Implemented conditional compilation for executing curl commands using _popen and _pclose on Windows.
- Ensured consistent handling of command execution across different operating systems.
- Updated response generation methods to maintain functionality in Windows environments.
- Enabled JSON support by default in CMake to resolve Windows build issues.
- Added checks for the existence of the JSON library and its target, providing clear error messages if missing.
- Updated README with instructions for building with AI features.
- Enhanced the build environment verification script for better feedback on setup issues and added checks for agent folder structure.
- Introduced new CMake presets for AI-enabled builds and collaboration support.
- Updated README.md to include detailed instructions for both local and network collaboration modes.
- Added setup requirements and steps for starting a collaboration server using Node.js.
- Enhanced feature descriptions for real-time collaboration, session management, and participant tracking.
- Improved clarity on how to host and join sessions in both collaboration modes.
- Added support for selecting between local and network collaboration modes in the AgentChatWidget.
- Implemented a UI for entering server URL and managing session details.
- Updated collaboration state management to include server URL and connection status.
- Improved layout of the collaboration panel with a table for session details and controls.
- Integrated a simple WebSocket client for handling network communication.
- Added CLI commands for starting and checking the status of the collaboration server.
- Updated the chat command to support new output formats: text, markdown, json, and compact.
- Modified the agent configuration to include output format settings.
- Enhanced the command line interface to handle new format options and provide detailed usage instructions.
- Improved the message printing logic in SimpleChatSession to format output based on the selected format.
- Added JSON and Markdown formatting for session metrics and messages.
- Updated help documentation to reflect changes in command usage and available options.
- Implemented `resource-search` command to allow fuzzy searching of resource labels.
- Added `dungeon-describe-room` command to summarize metadata for a specified dungeon room.
- Enhanced `agent` command handler to support new commands and updated usage documentation.
- Introduced read-only accessors for room metadata in the Room class.
- Updated AI service to recognize and handle new commands for resource searching and room description.
- Improved metrics tracking for user interactions, including command execution and response times.
- Enhanced TUI to display command metrics and session summaries.
- Added a `--verbose` flag to enable detailed debug output for the Gemini AI service.
- Updated `GeminiAIService` constructor to log initialization details when verbose mode is enabled.
- Modified `CreateAIService` to pass the verbose flag to the Gemini configuration.
- Enhanced command help in `ModernCLI` to categorize commands and provide detailed descriptions.
- Refactored `HandleSimpleChatCommand` to accept a pointer to `Rom` instead of a reference.
- Updated `ShowCategoryHelp` to display command categories and examples.
- Improved error handling and logging in `GeminiAIService` for better debugging.
- Added RecordingState structure to manage recording session details.
- Implemented SaveRecordingState and LoadRecordingState functions to handle recording state persistence.
- Enhanced HandleTestRecordCommand to support starting and stopping recording sessions with various options.
- Integrated gRPC calls for starting and stopping recordings in GuiAutomationClient.
- Updated ProposalRegistry to include sandbox directory and ROM path in ProposalMetadata.
- Implemented JSON parsing for Tile16Proposal to handle proposal creation from JSON input.
- Updated CMakeLists.txt to ensure proper linking of emulator targets.
- Added option to enable modular build with `YAZE_USE_MODULAR_BUILD`.
- Updated CMake configuration to support modular libraries for core, editor, graphics, GUI, and emulator functionalities.
- Refactored existing libraries to separate concerns and improve build times.
- Introduced new utility library `yaze_util` for low-level utilities.
- Adjusted CI and release workflows to accommodate the new build system.
- Updated various source files to reflect new include paths and modular structure.
- Enhanced YAML configuration handling in the agent component.
- Integrated yaml-cpp library into the project for YAML file parsing.
- Updated ConversationalAgentService to set ROM context in AI services.
- Extended AIService interface with SetRomContext method for context injection.
- Implemented SetRomContext in GeminiAIService and OllamaAIService.
- Enhanced PromptBuilder to load resource catalogues from YAML files.
- Added functions to parse commands, tools, examples, and tile references from YAML.
- Improved error handling for loading YAML files and added search paths for catalogues.
- Updated CMake configuration to fetch yaml-cpp if not found.
- Modified vcpkg.json to include yaml-cpp as a dependency.
- Implemented `overworld-find-tile` command in the agent for searching tiles by ID.
- Updated `README.md` and `AGENT-ROADMAP.md` to reflect new command and usage.
- Enhanced `overworld_inspect` module with tile matching functionality.
- Added `OverworldDescribeMap` command to summarize metadata for a specified overworld map.
- Introduced `OverworldListWarps` command to list overworld entrances and holes with their coordinates.
- Refactored existing `overworld.cc` to utilize new helper functions for parsing and validation.
- Created `overworld_inspect.cc` and `overworld_inspect.h` to encapsulate map and warp-related functionalities.
- Updated `ModernCLI` to register new commands and handle their execution.
- Modified `tool_dispatcher.cc` to support dispatching the new commands.
- Updated CMake configuration to include new source files for the inspection commands.
- Added support for JSON in CMake configuration for AI integrations.
- Implemented new tool commands: resource-list and dungeon-list-sprites.
- Created ToolDispatcher for managing tool command execution.
- Refactored CMake structure to include agent sources and improve build configuration.
- Updated agent roadmap and README documentation to reflect current status and next steps.
