Jun 15 09:15 feat: markdown-style feishu 08:48 fix: just rm symbol not include text 08:05 fix: voxcpm python no need source 07:29 feat: feishu voice voxcpm and edge-tts 04:09 feat: feishu voice tts 01:55 feat: feishu Jun 14 13:45 feat: feishu connect Jun 13 04:36 feat: add nvidia provider 02:19 feat: voice ok 02:01 feat: voice stt+tts just first have voice 00:31 feat: voice stt ok english Jun 12 17:13 feat: voice add fully-local STT (faster-whisper) + TTS (edge-tts) 06:29 feat: voice mode asr May 23 16:49 feat: desktop cd desktop && bun run tauri dev 11:32 feat: add opencode zen provider /login and enter opencode zen free then /model input free chose you want May 21 17:08 chore: fix prompt identity 16:32 fix: opencode login May 6 09:41 fix: refresh model list 09:00 fix: fetch active opencode model 07:20 feat: add new free provider opencode Apr 15 09:13 fix: rm Number(chatId) and use string save data project beyond chatId range Apr 13 02:03 feat: support auto-compact for "exceeds the available context size" errors Add error handler for alternative context overflow format used by some
API providers. This ensures auto-compact triggers regardless of the
specific error wording. Apr 12 13:34 feat: live refresh typing status Apr 8 06:13 fix: ban telegram log 06:05 test: WebSearchTool log Apr 4 18:05 fix: openrouter change to local but added to /model list 17:52 fix: auto fresh tui when from openrouter to local 17:25 fix: use telegram /login local to change to local model 17:13 fix: openrouter auto load api_key 12:32 feat: interactivateCommands in telegram 11:24 fix: telegram not get message because beyond int i use string solve this problem 11:03 fix: tui can recevie message and auto load gateway 07:06 feat: /telegram backend load Apr 3 03:30 fix: /login provider change Apr 2 20:35 feat: /login local model 17:45 init: verspercode v0.1.0 
