TerminallyLazy
TerminallyLazy
- Updated agent.py to include LiteLLM dependencies and improved serialization method. - Refactored models.py to streamline model handling and added LiteLLM support. - Enhanced memory.py for better document management and...
Not much to add here, models.py had significant changes, very minor changes otherwise.
This pull request introduces a major refactoring of the LLM provider integration by replacing direct API calls with LiteLLM. This change unifies how we interact with different LLM providers, simplifies...
1. Extension Model Call - python/extensions/message_autoformat/_10_autoformat_response.py:13 - Before: Used call_chat_model(prompt) - After: Uses call_utility_model(system, message) - This ensures auto-formatting uses the utility model and doesn't interfere with main conversation flow...
- Updated .gitignore to include new files related to research tools. - Improved agent.py with retry logic for API calls and enhanced error handling. - Added new modules for SakanaAI...
- Introduced SecretsManager class for handling secret values, including loading, saving, and masking. - Updated agent and tool classes to mask secrets in logs and responses. - Added a secrets...
- Added Kokoro TTS support in preload and run_ui scripts. - Introduced a new API endpoint for text-to-speech synthesis. - Updated settings to include TTS enable/disable option. - Refactored speech...
## Description This PR introduces a native Electron desktop shell for Agent Zero. It wraps the existing Docker-based setup in a desktop application, providing a connection wizard, native window management,...
# Summary Replace browser-based clock with backend-driven system time display to show the Linux container's time instead of the user's browser time. ## Problem - UI clock displayed frontend (browser)...
# Fix subordinate agent nudge reset and enable auto-nudge monitoring ## Summary This PR fixes a critical issue where manually nudging a subordinate agent would reset the entire agent chain...