7f955a59b9
Remove count_view_mes
2024-01-27 13:24:08 -05:00
1647e5ae49
Merge pull request #1734 from khanonnie/alternative-tokens
...
Implement Token Probabilities UI panel using logprobs
2024-01-26 03:39:25 +02:00
60044c18a4
Implement Token Probabilities UI using logprobs
2024-01-25 18:34:46 -06:00
1ef437f5f1
[feat] GENERATION_ENDED event
...
uses hideStopButton() to trigger the event, because all other paths are conditional and would require the event to be triggered in multiple functions, compared to hideStopButton() already being called at the end of all the generations
unblockGeneration() was another candidate, but it is not consistently executed to be viable
2024-01-26 00:53:27 +01:00
6012ee5f89
#1740 Open most recent chat when deleting current chat file
2024-01-25 18:55:38 +02:00
4abe87f103
#1742 Add /chat-manager command
2024-01-25 18:19:04 +02:00
1ae5a8bd66
#1630 Fix display mode regex depth calc
2024-01-25 02:53:39 +02:00
3f3529ef89
#1630 Add min/max depth for prompt/display regex scripts.
2024-01-24 22:48:58 +02:00
4985afd816
Extend external media checks
2024-01-24 19:14:40 +02:00
9f81ea3c1f
Allow double quotes inside of <tags>
2024-01-24 18:05:11 +02:00
4823bcf4ff
Add option to forbid external images
2024-01-24 15:47:54 +02:00
9b42be2334
Reset message editor before switching active chat
2024-01-23 11:00:33 +02:00
958cf6a373
Don't append name2 in non-instruct mode if continuing on first message
2024-01-21 23:20:29 +02:00
3cd935c0d2
Fix possible prompt overflow on message examples push-out
2024-01-21 23:13:01 +02:00
3cb9413541
#1718 Fix message search opening wrong chats
2024-01-20 20:13:41 +02:00
4f55824d7f
QR auto-execute on group member draft
2024-01-18 18:08:38 +02:00
b8445eb2cd
Add slash commands for instruct and context
2024-01-18 17:24:07 +02:00
f966c398ef
Increase preset command timeouts
2024-01-18 16:36:26 +02:00
e4d5eac6cf
Add world info to generate_before_combine_prompts event data
2024-01-15 17:45:50 +01:00
ed77f4763a
#1696 Don't cancel generation on first Escape press if editing a message
2024-01-15 03:45:31 +02:00
6086cedf2b
Use XHR to load HTML templates
2024-01-12 22:00:08 +02:00
4fe13fab8e
Customizable /gen instruct name
2024-01-12 19:16:42 +02:00
4e5f01d785
Merge pull request #1668 from valadaptive/macro-cleanups-1
...
Move substituteParams into its own module
2024-01-12 11:57:21 +02:00
05003ccf78
Remove silly debug logging
2024-01-12 04:38:40 -05:00
89a999cfd4
Move macro substitution to new module
...
substituteParams has become a thin wrapper around the new evaluateMacros
function, and will become more of a compatibility shim as refactorings
and rewrites are done.
2024-01-10 22:22:30 -05:00
3f6f32edad
Add {{mesExamplesRaw}} macro for story string
2024-01-10 14:11:02 +02:00
adf82f2ba8
#1663 Add last prompt line to quiet prompts
2024-01-09 01:14:23 +02:00
f7b1b490c7
Larger alternate greetings window
2024-01-06 19:59:48 +02:00
5f93c30a96
#1627 Bypass status check and custom model for textgen type
2024-01-05 19:15:07 +02:00
c69724e1da
Fix GUI Kobold
2024-01-02 10:28:34 +02:00
52637ccd39
Merge pull request #1619 from LenAnderson/worldinfo_updated-event
...
Add event when world info is updated
2024-01-01 18:35:23 +02:00
f53d937782
Fix mistral undefined name
2024-01-01 18:31:17 +02:00
9106696f2f
Render prompt manager when switching APIs
2024-01-01 17:06:10 +02:00
908bf7a61d
Merge branch 'staging' into generate-cleanups-3
2024-01-01 16:49:35 +02:00
8cd75cf03d
add event when world info is updated
2024-01-01 14:34:09 +00:00
30732ada32
Lint fix
2024-01-01 16:08:24 +02:00
ee70593a7e
Add world info to generate_before_combine_prompts event data
2023-12-28 17:03:36 +01:00
8dd4543e93
Remove macro from user messages when using bias
2023-12-28 11:19:56 +02:00
77b02a8d4b
Extract data.error check
2023-12-26 12:41:35 -05:00
0f8a16325b
Extract dryRun early return from finishGenerating
...
This means we only have to handle it in one place rather than two.
2023-12-25 03:48:49 -05:00
3c0207f6cb
Move "continue on send" logic out of Generate()
2023-12-25 03:48:49 -05:00
7899549754
Make "send message from chat box" into a function
...
Right now all it does is handle returning if there's already a message
being generated, but I'll extend it with more logic that I want to move
out of Generate().
2023-12-25 03:48:49 -05:00
1029ad90a2
Extract "not in a chat" check into guard clause
...
This lets us remove a layer of indentation, and reveal the error
handling logic that was previously hidden below a really long block of
code.
2023-12-25 03:48:49 -05:00
4fc2f15448
Reformat up Generate() group logic
...
The first two conditions in the group if/else blocks are the same, so we
can combine them.
2023-12-25 03:48:49 -05:00
0d3505c44b
Remove OAI_BEFORE_CHATCOMPLETION
...
Not used in any internal code or extensions I can find.
2023-12-25 03:48:49 -05:00
f53e051cbf
Lift precondition check out of processCommands
...
Instead of passing type and dryRun into processCommands, do the check in
Generate, the only function that calls it. This makes the logic clearer.
2023-12-25 03:48:49 -05:00
a9e074dae1
Don't recreate first message if generation was run at least once
2023-12-24 02:47:00 +02:00
db3bf42d63
Fix Firefox number arrows not updating the slider
2023-12-23 16:09:03 +02:00
09fd772a20
#1579 Add ooba character yaml import
2023-12-21 21:46:09 +02:00
4621834c87
Short formatting path for empty messages
2023-12-21 20:50:30 +02:00