- 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.
- Added support for AI agent services, including `ConversationalAgentService`, to facilitate user interactions through a chat interface.
- Implemented `ChatTUI` for a terminal-based chat experience, allowing users to send messages and receive responses from the AI agent.
- Updated `EditorManager` to include options for displaying the agent chat widget and performance dashboard.
- Enhanced CMake configurations to include new source files for AI services and chat interface components.
This commit significantly expands the functionality of the z3ed system, paving the way for a more interactive and user-friendly experience in ROM hacking.
- Added `HandleResourceListCommand` to list resources by type and format (table or JSON).
- Introduced `HandleDungeonListSpritesCommand` to retrieve and display sprites from specified dungeon rooms.
- Updated command handling in `agent.cc` to support new subcommands.
- Enhanced error handling for invalid inputs and missing ROM files.
This commit expands the functionality of the z3ed agent, enabling users to interact with game resources and dungeon sprites more effectively.
- Introduced a new `AGENT-ROADMAP.md` file outlining the strategic vision and implementation plan for the `z3ed` AI agent.
- Defined the core vision of transitioning to a conversational ROM hacking assistant with key features such as an interactive chat interface, ROM introspection, and contextual awareness.
- Detailed the technical implementation plan, including the development of a `ConversationalAgentService`, read-only tools for the agent, and user-facing TUI/GUI chat interfaces.
- Consolidated immediate priorities, short-term goals, and long-term vision for the agent's development.
This commit establishes a comprehensive roadmap for enhancing the z3ed agent's capabilities, paving the way for future AI-driven features and user interactions.
- Restructured CLI service source files to improve organization, moving files into dedicated directories for better maintainability.
- Introduced new AI service components, including `AIService`, `MockAIService`, and `GeminiAIService`, to facilitate natural language command generation.
- Implemented `PolicyEvaluator` and `ProposalRegistry` for enhanced proposal management and policy enforcement in AI workflows.
- Updated CMake configurations to reflect new file paths and ensure proper linking of the restructured components.
- Enhanced test suite with new test workflow generation capabilities, improving the robustness of automated testing.
This commit significantly advances the architecture of the z3ed system, laying the groundwork for more sophisticated AI-driven features and streamlined development processes.
- Updated the immediate action plan to focus on integrating `Tile16ProposalGenerator` and `ResourceContextBuilder` into agent commands, improving command handling and proposal generation.
- Implemented the `SetTile` method in the `Overworld` class to facilitate tile modifications based on the current world context.
- Enhanced error handling in command execution to ensure robust feedback during ROM operations.
- Created new files for `Tile16ProposalGenerator` and `ResourceContextBuilder`, enabling structured management of tile changes and resource labels for AI prompts.
This commit advances the functionality of the z3ed system, laying the groundwork for more sophisticated AI-driven editing capabilities.
- Added a comprehensive plan for integrating AI-driven workflows in overworld and dungeon editing, focusing on visual editing and ResourceLabels awareness.
- Established a phased implementation approach, starting with SSL support and basic Tile16 command integration.
- Outlined success metrics for both overworld and dungeon editing, ensuring AI can effectively understand and manipulate game data.
- Created a new document detailing the strategic shift towards specialized AI workflows, enhancing the overall functionality of the z3ed system.
This commit sets the foundation for advanced AI capabilities in ROM editing, paving the way for future enhancements and user-friendly features.
- Introduced SSL/HTTPS support in `z3ed.cmake` for secure communication, required for Gemini API and future collaborative features.
- Added options for OpenSSL integration and macOS Keychain support.
- Expanded `test_commands.cc` with new command handlers for running, replaying, and managing tests, improving modularity and usability.
- Updated command usage messages for clarity and consistency.
This commit enhances the security and functionality of the CLI, paving the way for more robust features in future iterations.
- Added new `test_common` module with helper functions for prompting and input handling.
- Introduced `test_common.cc` and `test_common.h` for shared functionality across test commands.
- Updated `z3ed.cmake` to include `test_common` in the build process.
- Refactored `test_commands.cc` to utilize new common utilities for improved readability and maintainability.
- Adjusted paths for source files in the build configuration to ensure proper linking.
This commit lays the groundwork for a more organized and modular approach to handling test commands, facilitating future enhancements and maintenance.
- Created LLM-INTEGRATION-SUMMARY.md detailing the integration plan for Ollama, Gemini, and Claude.
- Updated README.md to reflect the shift in focus towards LLM integration.
- Added quickstart_ollama.sh script to facilitate testing of Ollama integration with z3ed.
- Added `TestSuiteDefinition`, `TestGroupDefinition`, and `TestCaseDefinition` structures to represent test suite configurations.
- Implemented parsing logic for test suite definitions from a file in `test_suite_loader.cc` and `test_suite_loader.h`.
- Introduced `ReplayTestResult` structure in `gui_automation_client.h` to handle results from replaying tests.
- Added `ReplayTest` method in `GuiAutomationClient` to facilitate test replay functionality.
- Created `BuildTextSummary` and `BuildJUnitReport` functions in `test_suite_reporter.cc` for generating test reports.
- Implemented `WriteJUnitReport` function to save JUnit formatted reports to a specified output path.
- Enhanced error handling and logging throughout the new functionalities.
- Added a new helper function `CaptureHarnessScreenshot` to encapsulate SDL screenshot logic.
- Updated `ImGuiTestHarnessServiceImpl::Screenshot` to utilize the new screenshot helper.
- Enhanced `TestManager::CaptureFailureContext` to automatically capture screenshots and widget state on test failures.
- Introduced new fields in the `GetTestResultsResponse` proto for screenshot path, size, failure context, and widget state.
- Updated CLI and gRPC client to expose new diagnostic fields in test results.
- Ensured that screenshots are saved in a structured directory under the system's temp directory.
- Improved logging for auto-capture events, including success and failure messages.
- Created IT-08-SCREENSHOT-COMPLETION.md detailing the implementation of the Screenshot RPC, including technical summary, testing results, design decisions, and future work.
- Introduced IT-10-COLLABORATIVE-EDITING.md outlining the vision, user stories, architecture, implementation plan, and success metrics for real-time collaborative editing in YAZE.
- Added `verify-build-environment.ps1` for Windows users to check CMake, Git, Visual Studio, and submodules, with options for verbose output, automatic fixes, and cache cleaning.
- Introduced `verify-build-environment.sh` for macOS/Linux users, providing similar functionality with detailed output and automatic issue resolution.
- Updated documentation to include new verification steps and usage instructions for both scripts.
- Improved dependency checks and cache management in both scripts to ensure a smooth build setup.
- Added new test commands for GUI automation in `test_commands.cc`, including handling test runs, statuses, listings, and results.
- Refactored instances of `app::core::AsarWrapper` to `core::AsarWrapper` across multiple files for consistency.
- Updated CMake configuration to include new test command files.
- Modified integration and unit tests to reflect the changes in AsarWrapper usage.
- Ensured proper error handling and output formatting for test commands.
- Introduced TestRecorder class to capture GUI automation RPCs and export them as JSON test scripts.
- Implemented StartRecording, StopRecording, and ReplayTest RPCs in ImGuiTestHarnessService.
- Updated imgui_test_harness.proto to include new RPCs and message definitions for recording and replay.
- Created TestScriptParser for reading and writing test scripts in JSON format.
- Enhanced DiscoverWidgetsRequest and DiscoveredWidget messages with detailed comments for clarity.
- Added ScopedSuspension mechanism in TestRecorder to manage recording state.
- Added `DiscoverWidgets` RPC to the ImGuiTestHarness service for enumerating GUI widgets.
- Introduced `WidgetDiscoveryService` to handle widget collection and filtering based on various criteria.
- Updated `agent gui discover` command to support new options for filtering and output formats.
- Enhanced `GuiAutomationClient` to facilitate widget discovery requests and responses.
- Added necessary protobuf messages for widget discovery in `imgui_test_harness.proto`.
- Updated CLI command handling to include new GUI discovery functionality.
- Improved documentation for the `agent gui discover` command with examples and output formats.
- Refactored the HandleTestCommand to support subcommands: status, list, and results.
- Implemented HandleTestStatusCommand to fetch and display the status of a test by ID.
- Added HandleTestListCommand to list tests with optional filters for category and status.
- Created HandleTestResultsCommand to retrieve detailed results for a specific test execution.
- Introduced new structures for test status details, test summaries, and results.
- Updated GuiAutomationClient to support gRPC calls for fetching test status and results.
- Enhanced the ModernCLI to reflect new command usage for test operations.
- Added JSON and YAML formatting for test results output.
- Introduced new gRPC service methods: GetTestStatus, ListTests, and GetTestResults for enhanced test introspection.
- Defined corresponding request and response message types in the proto file.
- Implemented test harness execution tracking in TestManager, including methods to register, mark, and retrieve test execution details.
- Enhanced test logging and summary capabilities to support introspection features.
- Updated existing structures to accommodate new test management functionalities.
- Added Policy Evaluation Framework with core components including PolicyEvaluator service, policy types, severity levels, and GUI integration.
- Created documentation for the Policy Evaluation Framework detailing implementation, configuration, and testing plans.
- Introduced Remote Control Agent Workflows documentation, outlining gRPC interactions for automated editing in YAZE.
- Removed outdated Test Validation Status document and replaced it with updated Widget ID Next Actions documentation.
- Established widget registry integration for improved remote control capabilities and added support for hierarchical widget IDs.
- Enhanced test harness functionality to support widget discovery and interaction through gRPC.
