2.5.0

• Added provider for DeepSeek (in Chat with Files mode, beta).
• Added new models: OpenAI o1, Llama 3.3, DeepSeek V3 and R1 (API + local, with Ollama).
• Added tool calls for OpenAI o1.
• Added native vision for OpenAI o1.
• Fix: tool calls in Ollama provider.
• Fix: error handling in stream mode.
• Fix: added check for active plugin tools before tool call.

2.4.57

• Logging fix.

2.4.56

• Improved tab switching and focus change.
• Improved global keyboard shortcuts handling.

2.4.55

• Added a new option in settings: Audio -> Recording timeout.
• Added a new option in settings: Audio -> Enable timeout in continuous mode.

2.4.54

• Audio output switched from PyGame to PyAudio. It may be necessary to manually connect Alsa in Snap version with: "sudo snap connect pygpt:alsa".
• Added audio output volume progress bar.

2.4.53

• Fix: issue #89

2.4.52

• Improved audio input button visibility toggle.
• Fix: check for required arguments - issue #88.
• UI Fixes.

2.4.51

• Added a "Continuous recording" mode under Audio Input in the Notepad tab, allowing for recording long voice notes and real-time auto-transcription. (beta)
• A new option has been added in Settings -> Audio -> Continuous recording auto-transcribe interval.

2.4.50

• Refactored audio input core.
• Added audio input volume progress bar.

2.4.49

• Fix: stream render in Assistants mode.
• Fix: items remove in context regen/edit.