Starstruk Logo MarkStarstruk

v1.5.1-beta.3

altic-dev/FluidVoicev1.5.1-beta.3Dec 20, 2025by altic-dev

AI Summary

Beta release refining AI features and stability fixes introduced in previous beta versions.

Key Highlights

  • Added support for displaying AI 'thinking tokens' (model reasoning).
  • Added toggle in Settings to enable/disable debug logs.
  • Added ability to enable/disable saving transcription history.
  • Added enable/disable toggle for Command Mode and Write Mode shortcuts.
  • Fixed race condition checks during longer transcription sessions.

New Features

  • AI thinking tokens support.
  • Debug logging toggle.
  • Transcription history toggle.
  • Mode shortcut toggles.
  • Transcription stability fixes.

Full Release Notes

# FluidVoice 1.5.1-beta.3

## New Features

**AI Thinking Tokens**
- Added support for displaying AI "thinking tokens" (model reasoning)
- Improved parsing for thinking token blocks across different LLM providers
- Enhanced LLMClient to properly handle and separate thinking content from response content

**Debug Logging Toggle**
- Added a toggle in Settings to enable/disable debug logs
- Debug logger now respects the toggle setting for cleaner console output

**Transcription History Toggle**
- Added ability to enable/disable saving transcription history

**Mode Shortcuts**
- Added enable/disable toggle for Command Mode and Write Mode 

## Bug Fixes

**Transcription Stability**
- Fixed race condition checks during longer transcription sessions on some devices

**Terminal Service**
- Fixed JSON fallback escaping in TerminalService for more reliable command execution

**Input Device Picker**
- Fixed issue where the audio input device picker could sometimes appear empty