This commit is contained in:
Paul Gauthier 2025-01-10 14:20:50 -08:00
parent 38678fafc1
commit dc5b5896a9
3 changed files with 7 additions and 5 deletions

View file

@ -4,9 +4,10 @@
- Prompts to help DeepSeek work better when alternating between `/ask` and `/code`.
- Streaming pretty LLM responses is smoother and faster for long replies.
- Bare `/ask`, `/code` and `/architect` commands now switch the chat mode.
- Streaming automatically turns of for model that don't support it
- Can now switch to/from `/model o1` and a streaming model
- Pretty output remains enabled even when editing files with triple-backtick fences
- Bare `/ask`, `/code` and `/architect` commands now switch the chat mode.
- Increased max chat history tokens limit from 4k to 8k.
- Turn off fancy input and watch files if terminal is dumb.
- Added support for custom voice format and input device settings.