Share content-addressed parsing and embedding caches across isolated test runs, fingerprint relevant dependencies and model assets, and remove implicit UI warm-up. Add realistic two-round Skill delivery evaluation and cache regressions.
- Implement end-to-end tests for user skill creation and editing, ensuring proper handling of name conflicts and partner bindings.
- Add tests for importing skills from a directory, verifying that existing resources are preserved or replaced correctly.
- Introduce tests for skill partner budget management, ensuring that skills are isolated between partners and that budget limits are enforced.
- Enhance existing tests to validate the integration of AI processes with user skills, ensuring that updates to skills are reflected in AI outputs.
- Create necessary fixtures and scripts to support the new tests, including skill definitions and rules for processing.
Copy complete Skill folders into shared user data with per-partner enable bindings. Separate load_skill instruction context from load_toolset registration, state, prompts and tool-budget eviction.
Revalidate instruction bindings across inference, compaction and restore. Add management UI, safe import and storage migration coverage, real graph regressions, and persisted snapshot recovery checks.
Signed-off-by: Lingu <132213669+AntonyLang@users.noreply.github.com>
- Added `findInstalledWindowsShortcut` to locate Windows shortcuts for installed applications.
- Integrated `launchEntryPath` into the E2E application preparation process to improve launch entry tracking.
- Removed loopback URL checks and related functions from `httpPageFetch.ts` to simplify HTTP fetching logic.
- Updated `web/index.ts` to streamline HTTP page fetching logic and remove unnecessary loopback checks.
- Modified E2E tests to correctly retrieve Electron process IDs and improve test reliability.
- Introduced `isExpectedMacDesktopTeardownExit` to classify macOS application exits more accurately.
- Enhanced Electron app launch process to support desktop launch configurations and ensure proper teardown.
- Added tests for desktop launch configurations to ensure sensitive data is not exposed.
- Improved error handling and logging during Electron app launches and exits.
- Added a modal for opening help website with confirmation dialog.
- Integrated help button in settings sidebar to trigger help modal.
- Improved layout responsiveness for settings sections across different languages.
- Updated selectors for cache cleanup and added new cache-related tests.
- Enhanced partner cache preview functionality to include total bytes and skipped counts.
- Refactored e2e tests for settings help entry and partner cache cleanup to validate new features.
- Adjusted Electron app launch configuration to ensure correct working directory.
- Updated ModelSource type to include 'huggingface'.
- Enhanced MODEL_SOURCE_LABELS for better clarity.
- Introduced defaultModelSource function to determine default source based on service route.
- Modified AppSettings to include language and serviceRoute.
- Created end-to-end tests for language and service route settings.
- Added unit tests for application language and service preferences.
- Updated free models test to reflect new catalog naming conventions.
- Enhanced official API tests to ensure correct handling of service regions.
- Adjusted release artifact tests to accommodate internationalization.
- Updated SQLite migration and storage tests to include new preferences.
- Updated legacy document references in various test files to reflect new document names and paths.
- Modified user input prompts in tests to align with the new document content and context.
- Adjusted assertions in tests to ensure they check for the correct content based on the updated documents.
- Added new test fixtures and removed outdated ones to maintain test integrity.
- Ensured all changes maintain the functionality of the tests while improving clarity and relevance.
- Implemented useWpsIntegrationFeedback hook to manage WPS integration issues and display appropriate messages.
- Updated OfficeFileReview component to show integration issues when file navigation fails.
- Improved TextFileDiffViewer to indicate whether the current file is editable or read-only.
- Added WPS integration manual URL for user guidance on enabling WPS add-ins.
- Enhanced WorkbenchDocumentPreviewPanelBase to open the WPS integration manual on button click.
- Introduced WpsIntegrationIssue type and related constants for better type safety and clarity.
- Updated tests to cover new WPS integration features and ensure proper functionality.
- Refactored existing code to accommodate new WPS integration logic and improve maintainability.
- Updated the file open menu to improve user experience with a new layout and functionality, including the ability to set preferred applications and reveal containing folders.
- Refactored the text file diff viewer to include a toolbar for navigating differences, with improved accessibility and visual feedback for actions like folding unchanged lines.
- Added localization support for various messages in the Monaco editor.
- Implemented CSS changes for better styling of dropdown menus and buttons in the workbench.
- Enhanced e2e tests to cover new functionalities and ensure proper behavior of the file open menu and text file diff viewer.
- Added functionality to append unchanged context to the preview file in `text-file-apply-preview-and-revert.e2e.test.ts`.
- Updated diff viewer selectors to improve line removal and addition detection.
- Implemented review edit and undo functionality with assertions in `text-file-apply-preview-and-revert.e2e.test.ts`.
- Enhanced the handling of omitted lines in the diff viewer.
- Modified the application of default settings in `file-preview-actions.e2e.test.ts`.
- Improved WPS Office reload and navigation tests in `wps-office-reload-on-write-and-revert.e2e.test.ts` and added a new test for WPS audit navigation.
- Refactored Excel cell interaction methods in `excel.ts` to support dynamic layout handling.
- Updated WPS Office coverage targets to include file name in prompts and added fixture preparation logic.
- Cleaned up WPS environment handling to ensure proper resource management during tests.
- Added FreeModelCatalogService for managing free model metadata and caching.
- Introduced token management for free models, including token refresh logic.
- Updated API calls to use free model endpoints and handle authorization.
- Enhanced model selection logic to accommodate free models.
- Improved tests for free model functionality and caching behavior.
- Update `human-harness.md` to clarify image caching and logging behavior.
- Modify `workbench.md` to improve user experience with free models lacking vision capabilities.
- Add new test case `human-read-image-no-vision` to validate behavior when using free models without vision support.
- Enhance `generate-ai-tool-prompt-audit.mts` to include error descriptions for `read_image` failures.
- Implement checks in `agentControl` to prevent image processing with unsupported models.
- Update `ChatPage.tsx` to ensure context usage is refreshed correctly after partner state changes.
- Extend tests for `read_image` functionality to cover various model configurations and ensure proper error handling.
- Refactor `model-selector-and-provider-error.e2e.test.ts` to verify context usage after different run states.
- Adjust `realAiDepsFactory.ts` and `test-types.ts` to accommodate new model configurations and types.
- Updated knowledge test plans to clarify the cancellation behavior of workspace indexing and its interaction with the backend.
- Revised assertions in the `workspace-index-cancel-contract` test to ensure completed entries are preserved and unfinished entries are reverted correctly.
- Enhanced the `prepare-workspaces-sequentially` test to validate that subsequent addresses do not start after the first is cancelled.
- Removed obsolete `cnipa-http.host.test.ts` and `electronBareNavigateHost.mjs` files as they are no longer needed.
- Added new assertions in the `workspace-index-job-progress.test.ts` to verify the handling of completed and unfinished job states.
- Improved the `workspace-index-worker-contract.test.ts` to ensure proper cancellation behavior during embedding processes.
- Updated E2E tests for right panel layout and tab interactions to include resizing functionality.
- Enhanced clarity and specificity in knowledge test documentation regarding session options and thread management.
- Revised settings test descriptions to improve accuracy in reflecting UI behavior and expected outcomes.
- Improved assertions in workspace and web tests to ensure comprehensive coverage of UI interactions and state management.
- Adjusted e2e test cases for workspace cancellation scenarios to accurately reflect expected behavior post-cancellation.
- Updated descriptions in terminal tests to clarify execution context and expected outputs.
- Refined messages in partner cache cleanup tests to better align with acceptance criteria.
- Revised the test documentation to improve clarity and organization, including renaming sections and updating headings for better navigation.
- Consolidated test case rules and execution processes into a more coherent format.
- Removed redundant boundary definitions in the UI style document, focusing on design language and visual consistency.
huangyuan