- Eliminate support for LLM_DISABLE_THINKING and LLM_REASONING_EFFORT in config, code, and tests
- Simplify LLM thinking level logic to rely solely on LLM_THINKING_LEVEL
- Refactor LLMHelper and related endpoints to remove legacy parameter handling
- Update system API and test utilities to match new configuration structure
- Minor code cleanup and formatting improvements
- Integrate voice message handling: detect and extract audio references from Telegram and WeChat messages, route to agent with voice reply preference.
- Add voice provider abstraction and OpenAI-based TTS/STT implementation.
- Implement agent tool `send_voice_message` for generating and sending voice replies, with fallback to text if voice is unavailable.
- Extend agent prompt and context to support voice reply instructions.
- Update notification and message schemas to support audio fields.
- Add Telegram and WeChat voice sending logic, including audio file conversion and temporary media upload for WeChat.
- Add tests for voice helper and agent voice routing.
Align endpoint/module type hints and config reload handling while updating base Python image and package pins to improve build/runtime compatibility.
Made-with: Cursor
- Use distributions() in __get_installed_packages for installed packages
- Use packaging.requirements.Requirement, drop pkg_resources dependency
- __standardize_pkg_name: normalize dots to underscores (PEP-style)
- Keep max version when multiple distributions exist for same package
Made-with: Cursor
Implement rTorrent downloader module via XML-RPC protocol, supporting both HTTP (nginx/ruTorrent proxy) and SCGI connection modes. Add RtorrentModule implementing _ModuleBase and _DownloaderBase interfaces with no extra dependencies.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
