Removes the `ToolHistoryManager` and its associated functionalities, including history recording, querying, and prompt generation. This simplifies the architecture by decoupling tool execution history from the core logic.
The tool caching mechanism is now directly integrated into the `ToolExecutor` by wrapping the `execute_tool_call` method. This ensures that caching is applied consistently for all tool executions that have it enabled, improving performance and reducing redundant calls.
- Deletes `src/common/tool_history.py`.
- Removes tool history related functions from `prompt_builder.py` and `tool_api.py`.
- Adds a `wrap_tool_executor` function in `cache_manager.py` to apply caching logic directly to the `ToolExecutor`.
Cleaned up various files by removing unused or redundant import statements to improve code readability and reduce potential confusion. No functional changes were made.
Replaces the L2 cache layer's SQLite implementation with an async SQLAlchemy-based database model (CacheEntries). Updates cache_manager.py to use db_query and db_save for cache operations, adds semantic cache handling with ChromaDB, and introduces async cache clearing and expiration cleaning methods. Adds the CacheEntries model and integrates it into the database API.
Introduces a ToolCache class to manage caching of tool invocation results with support for both exact and approximate (similarity-based) query matching. Includes methods for cache retrieval, storage, expiration, cleanup, and statistics. This helps improve efficiency by reusing previous results and reducing redundant tool executions.
Co-Authored-By: tt-P607 <68868379+tt-P607@users.noreply.github.com>
