- Added missing newlines and improved formatting in `CLAUDE.md` for better readability.
- Updated command instructions in the development guide to use `uv run` for running the server and tests.
- Enhanced type hinting in `consumer.py` for better clarity on the `facts` variable.
- Corrected a typo in the docstring of the `chat` function in `agent.py`.
- Refined type checks in `sessions.py` to use `isinstance` for better practice.
- Improved message formatting in `history.py` to ensure consistent output.
- Cleaned up test files by removing unnecessary imports and improving readability.
These changes enhance the overall clarity and maintainability of the codebase.
- Added environment variables for fake API keys in `conftest.py` to facilitate testing.
- Refactored mock functions in tests to utilize global mocks for LLM calls, improving consistency and reducing redundancy.
- Updated various test cases to rely on the new mocking structure, ensuring accurate simulation of LLM responses and fact extraction.
- Removed direct calls to model clients in tests, replacing them with mocks to streamline test execution and maintain isolation.