- 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>
- 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.
- Removed unused 'wait' status and replaced with 'learning' in assistant execution types.
- Enhanced assistant execution summary text for various tool actions, including improved translations for user feedback.
- Refactored logic for building execution summaries to streamline handling of tool statuses and text segments.
- Updated tests to reflect changes in execution summary behavior and ensure accurate assertions for tool actions.
- Improved terminal command handling in tests, allowing for detached execution scenarios and refining assertions for terminal command results.
- Adjusted e2e tests to validate rendering of process activities and final answers, ensuring compliance with updated requirements.
- Updated architecture documentation to clarify the generation of AI tool prompt audit examples.
- Revised workbench test plan to specify Excel tool coverage and ensure accurate validation of user workflows without redundant operation enumeration.
- Modified script comments for generating AI tool prompt audit to reflect new command usage and clarify that generated examples are not stored in the repository.
- Changed the web search tool to differentiate between 'fetch' and 'search' types using a discriminated union in the input schema.
- Updated the handling of web search results to return structured outputs for both fetching a URL and searching for content.
- Refactored related functions and types to accommodate the new structure, including output types and error handling.
- Adjusted tests to reflect the new input structure and ensure proper functionality for both fetching and searching scenarios.
- Enhanced the rendering of web search results to align with the new output format.
- Added input fields to OutputCase type for better context in terminal and file operations.
- Updated terminal run cases to include command explanations and refined output data.
- Expanded text file edit cases to cover batch replacements and detailed error messages.
- Enhanced knowledge base search and document listing with additional metadata and improved error handling.
- Improved PDF and DOCX handling with more comprehensive data structures and examples.
- Refined Excel operations to include detailed input parameters and error messages.
- Added new image generation cases with specific input requirements and output details.
- Added `renderFileEnvelope`, `renderNumberedFileLines`, and `formatReadRangeFooter` in `envelope.ts`.
- Introduced `renderGroupedHeader`, `renderGroupedFooter`, `joinGroupedSections`, and `renderNoMatches` in `grouped.ts`.
- Created `renderUntrustedWebContent` in `markdownWeb.ts` to handle untrusted web content rendering.
- Developed prose rendering functions in `prose.ts` including `renderProse`, `renderFileMutationProse`, and `renderResourceMutationProse`.
- Implemented shared utility functions in `shared.ts` for XML escaping and line wrapping.
- Added terminal rendering functions in `terminal.ts` for output streams and markers.
- Updated terminal tool schemas to reflect changes in output types and statuses.
- Refactored terminal status handling in `terminalToolStatus.ts` for better clarity and consistency.
- Enhanced terminal tool tests to validate new status mappings and output structures.
- Created unit tests for model tool result renderers to ensure correct output formatting.
- Implemented a new script `generate-ai-tool-prompt-audit.mts` that generates a markdown document for auditing AI tool prompts.
- The script extracts input and output specifications from the tool registry and formats them into a structured markdown format.
- Includes detailed examples for each tool, enhancing documentation clarity and usability.
huangyuan