- 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.
- Introduced `ToolDispatcher` class to handle tool calls from the AI agent, allowing for dynamic execution of commands based on user requests.
- Updated `ConversationalAgentService` to integrate tool dispatching, enabling the agent to respond to tool calls and manage execution results.
- Enhanced `AgentResponse` structure to include a list of tool calls, facilitating communication between the AI and the tool dispatcher.
- Modified AI service implementations to parse and include tool calls in responses, improving the agent's interactive capabilities.
This commit significantly enhances the z3ed system's ability to manage and execute tool calls, paving the way for more complex interactions in ROM hacking.
