Only send the 30 most recent ai questions and responses to the model
when making requests. This prevents the amount of data being sent from
getting too big.
Adds new functionality on the backend that will merge any file from the
config directory that matches `<partName>.json` or `<partName>/*.json`
into the corresponding config part (presets, termthemes, etc.). This
lets us separate the AI presets into `presets/ai.json` so that we can
add a dropdown in the AI preset selector that will directly open the
file so a user can edit it more easily. Right now, this will create a
preview block in the layout, but in the future we can look into making
this block disconnected from the layout.
If you put AI presets in the regular presets.json file, it will still
work, since all the presets get merged. Same for any other config part.
Shallow copy the presets when updating `display:name` so that the
appending of the model name for the default preset doesn't accumulate
every time the tab refreshes.
closes#1040
This will print error messages to the chat when there is an error
getting an ai response. The actual content of the responses are not
forwarded to the models in future requests.
<img width="389" alt="Screenshot 2024-10-09 at 2 36 13 PM"
src="https://github.com/user-attachments/assets/e6c6b1c1-fa19-4456-be3b-596feaeaafed">
This change adds
- performance improvements for ai chat
- new ai chat user interface
- open blank files with codeedit
- fix for userinput password modal
This PR swaps usage of the `uuid` library for the built-in
`crypto.randomUUID` function, which is available in both NodeJS and the
browser. The built-in function is around 12x faster than the `uuid`
library. The strings produced by the built-in function are fully
compatible with the UUIDv4 standard, so it's an easy switch.
