| Age | Commit message (Collapse) | Author | Lines |
|
|
|
* feat: support function calling
* fix on Windows OS
* implement multi-steps function calling
* fix on Windows OS
* add error for client not support function calling
* refactor message data structure and make claude client supporting function calling
* support reuse previous call results
* improve error handling for function calling
* use prefix `may_` as indicator for `execute` type fucntions
|
|
|
|
|
|
* feat: support vision
* clippy
* implement vision
* resolve data url to local file
* add model openai:gpt-4-vision-preview
* use newline to concate embeded text files
* set max_tokens for gpt-4-vision-preview
|
|
* refactor: redesign render
- if stdout is not terminal, just write reply text to stdout
- rename repl_render_stream to markdown_stream
- deprecate cmd_render_stream
- use raw_stream to just print streaming reply text
* optimize rendering error
* optimize render_stream
|
|
|
|
|
|
|
|
- move model_info.rs/message.rs to clients/
- rename SharedConfig to GlobalConfig
|
|
- rewrite Repl, remove ReplHandler
- move ReplyStreamHandler to repl/ and rename it to ReplyHandler
- deprecate utils::print_now
- refactor session info
|
|
|
|
|
|
|
|
* feat: support textwrap
* improve cmd_render_stream
* done cmd_render_stream
* add `-w` alias to `--wrap`
* done repl_render_stream
* add `config.wrap_code`
* remove cached config.wrap_width
* fix unxpected duplicate lines on kitty
* refactor markdown render
* improve render
* fix test
|
|
|
|
|
|
|
|
There are two ways to enable the light theme:
- add `light_theme: true` to config.yaml
- use `AICHAT_LIGHT_THEME=true` env var
|
|
|
|
* chore: optimize newline again
command mode: should no extra newline
chat mode: should have one newline
* fix windows newline
* fix macos newline
|
|
|
|
|
|
|
|
* feat: command mode supports stream out
* update cli
|
|
|
|
|
|
* refactor: use syntect for highlight, abandon mdcat
* split src/render.rs to sub modules. embed a default theme
* simulate typing effect.
* fix format
|