Fix: Beta testing fixes#16
Merged
phernandez merged 26 commits intomainfrom Mar 1, 2025
Merged
Conversation
- Remove knowledge.py tools and related test file - Update tools/__init__.py to remove references - Remove get_entity CLI command - Simplify codebase by removing unused code These tools provided low-level access to the knowledge graph but were superseded by the more intuitive document-centric tools in notes.py. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Update CLAUDE.md with enhanced project documentation - Fix typo in JSON Canvas spec reference - Add detailed examples of tool usage - Expand AI-Human collaboration section - Update prompt module docstrings for consistency 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Split tools from memory.py into individual files (build_context.py, recent_activity.py) - Split tools from notes.py into individual files (read_note.py, write_note.py) - Update imports in __init__.py to import from new locations - Update imports in prompts package to reference new file locations - Each tool is now in its own dedicated file for better modularity - Maintain backward compatibility via __init__.py exports This refactoring makes each tool completely independent with its own dedicated file for implementation, documentation, and imports, while preserving the existing public API. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Rename read_resource to read_file for clarity and consistency - Add comprehensive docstrings to read_file with examples - Fix docstring in read_note to match implementation - Enhance search docstring with detailed param descriptions and examples These changes improve the clarity of the documentation, provide more helpful examples, and make the API more intuitive by renaming the read_resource tool to read_file. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
Update MCP tools and prompts documentation in CLAUDE.md to reflect: - Improved organization with categorized tools - More detailed parameter information - Added read_file tool (renamed from read_resource) - Expanded prompt descriptions with clear functionality 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Add more user-friendly error messages for different HTTP status codes - Use appropriate logging levels for different error types (info for 4xx, error for 5xx) - Provide specific error messages for common error scenarios - Extract path from URL for cleaner error messages - Handle type errors for proper type checking This improves the user experience by providing more helpful error messages and reduces log noise by only logging server errors at the error level. Client errors like 404 Not Found are now logged at info level with clearer messages. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Add is_success attribute to MockResponse to match real HTTPX response - Update error message assertions to check for specific user-friendly messages - Add new test for get_error_message function to verify status code handling - Test URL object handling and resource name extraction 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Remove test for removed get-entity CLI command - Update assertion in test_read_note_not_found to expect new error message format - Simplify test_tool_resource tests to use actual fixtures 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Add `# pragma: no cover` annotations to utils.py for unreachable or edge case paths - Add new Makefile target for running tests on specific modules with coverage - Ensure full test coverage for error handling code paths - Mark error conditions that are impossible to test with # pragma: no cover 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Added test_read_note_non_error_status to test error message path - Achieved 100% test coverage for read_note.py - Test verifies the error message format for non-200 status codes - This completes testing for all code paths in read_note 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- return permalinks instead of ids in search and context results - fix sync issues
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.