KCaverly
ec1b4e6f85
added initial working status in inline assistant prompt
2023-10-05 13:01:11 +03:00
KCaverly
68c37ca2a4
move embedding provider to ai crate
2023-09-22 09:33:59 -04:00
KCaverly
48e151495f
introduce ai crate with completion providers
2023-09-21 22:44:56 -04:00
KCaverly
5f6334696a
rename ai crate to assistant crate
2023-09-21 21:54:59 -04:00
Joseph T. Lyons
5df9a57a8b
Add assistant events ( #2978 )
...
Add assistant events
Release Notes:
- N/A
2023-09-15 15:25:35 -04:00
Nate Butler
24974ee2fa
Unify icons using multiple variants, remove all unused icons
2023-09-15 12:50:49 -04:00
Antonio Scandurra
925da97599
Don't dismiss inline assistant when an error occurs
2023-09-15 12:32:37 +02:00
Kirill Bulatov
9f5314e938
Unify highlights in *Map
2023-09-14 22:08:12 +03:00
Antonio Scandurra
127d03516f
Diff lines one chunk at a time after discovering indentation
2023-09-13 11:57:10 +02:00
Antonio Scandurra
b8c437529c
Never use the indentation that comes from OpenAI
2023-09-13 11:40:28 +02:00
Antonio Scandurra
6d9333dc3b
Add a failing test for codegen autoindent
2023-09-11 14:35:15 +02:00
Antonio Scandurra
02078140c0
Extract code generation logic into its own module
2023-09-11 11:25:37 +02:00
Antonio Scandurra
d868ec920f
Avoid duplicate entries in inline assistant's prompt history
2023-09-01 09:15:29 +02:00
Max Brunsfeld
eecd4e39cc
Propagate Cancel action if there is no pending inline assist
2023-08-31 11:09:36 -07:00
Antonio Scandurra
bf67d3710a
Remove trailing backticks when assistant ends with a trailing newline
2023-08-30 12:08:14 +02:00
Antonio Scandurra
5f6562c214
Detect indentation from GPT output
2023-08-30 12:07:58 +02:00
Antonio Scandurra
c6f4390511
Retain search history for inline assistants
...
This only works in-memory for now.
2023-08-30 11:30:51 +02:00
Antonio Scandurra
5c498c8610
Show inline assistant errors
2023-08-30 11:04:48 +02:00
Antonio Scandurra
87e25c8c23
Use model from conversation when available
2023-08-29 18:25:02 +02:00
Antonio Scandurra
16422a06ad
Remember whether include conversation was toggled
2023-08-29 18:25:02 +02:00
Antonio Scandurra
72413dbaf2
Remove the ability to reply to specific message in assistant
2023-08-29 14:51:00 +02:00
Antonio Scandurra
2332f82442
More polish
2023-08-29 14:41:02 +02:00
Antonio Scandurra
08df24412a
Delete less aggressively
2023-08-29 14:31:58 +02:00
Antonio Scandurra
c2b60df5af
Allow including conversation when triggering inline assist
2023-08-29 14:08:16 +02:00
Antonio Scandurra
ccec59337a
📝
2023-08-28 14:46:05 +02:00
Antonio Scandurra
52e1e014ad
Allow redoing edits performed by inline assistant after cancelling it
2023-08-28 14:42:52 +02:00
Antonio Scandurra
8c4d2ccf80
Close inline assist when the associated transaction is undone
2023-08-28 14:23:42 +02:00
Antonio Scandurra
44f554f489
Merge remote-tracking branch 'origin/main' into ai-refactoring
2023-08-28 12:16:24 +02:00
Antonio Scandurra
1fb7ce0f4a
Show icon to toggle inline assist
2023-08-28 12:13:44 +02:00
Antonio Scandurra
d804afcfa9
Don't auto-indent when the assistant starts responding with indentation
2023-08-28 11:57:02 +02:00
Piotr Osiewicz
07b9c6c302
language: Make Buffer::new take an explicit ID ( #2900 )
...
See Linear description for the full explanation of the issue. This PR is
mostly a mechanical change, except for the one case where we do pass in
an explicit `next_id` instead of `model_id` in project.rs.
Release Notes:
- Fixed a bug where some results were not reported in project search in
presence of unnamed buffers.
2023-08-28 11:51:50 +02:00
Antonio Scandurra
937aabfdfd
Extract a strip_markdown_codeblock function
2023-08-28 11:24:55 +02:00
Antonio Scandurra
55bf45d265
Add disabled style for prompt editor after confirming
2023-08-26 12:07:03 +02:00
Antonio Scandurra
658d616b96
Allow multiple inline assistant highlights at once
2023-08-26 11:55:47 +02:00
Antonio Scandurra
c8e5c3963b
Clear selection when deploying inline assistant
2023-08-26 09:52:01 +02:00
Max Brunsfeld
404f76739c
Format let-else statements
2023-08-25 10:11:32 -07:00
Antonio Scandurra
c4966ff57a
Remove warning
2023-08-25 17:35:14 +02:00
Antonio Scandurra
75a6a94e96
Add placeholder text for inline assistant prompts
2023-08-25 17:24:26 +02:00
Antonio Scandurra
b101a7edff
Cancel last inline assist when escaping from the editor
2023-08-25 15:54:52 +02:00
Antonio Scandurra
fdbf4680bb
Ensure the inline assistant works with gpt-3.5
2023-08-25 15:39:10 +02:00
Antonio Scandurra
27c90f12f6
Merge remote-tracking branch 'origin/main' into ai-refactoring
2023-08-25 13:37:32 +02:00
Antonio Scandurra
0444b5a775
💄
2023-08-25 13:36:52 +02:00
Antonio Scandurra
971c833e80
Improve background highlighting of inline assists
2023-08-25 12:35:36 +02:00
Antonio Scandurra
144f5c5d41
Use a left bias for the prompt editor
2023-08-25 12:25:43 +02:00
Antonio Scandurra
66a496edd7
Allow generating code without editing it
2023-08-25 12:16:28 +02:00
Antonio Scandurra
c1bd035875
Rework inline assistant
2023-08-25 11:39:27 +02:00
Antonio Scandurra
805e44915c
WIP
2023-08-24 17:23:12 +02:00
Antonio Scandurra
cbf7160054
Improve scoring
2023-08-24 16:32:55 +02:00
Antonio Scandurra
c1d9b37dbc
Move to an inline refactoring prompt
2023-08-24 15:46:18 +02:00
Antonio Scandurra
2468506189
Always clear refactoring text highlights, even if an error occurs
2023-08-24 14:29:05 +02:00
