Cohee
4a6705cea8
Prompt manager configuration fixes ( #1078 )
...
* Refactor oai preset change event into before and after
* Simplify and reinforce prompt manager render without character
* Check if main prompt exists before adding nsfwAvoidance
* Sanitize prompt manager configuration on preset loading
---------
Co-authored-by: maver <kentucky@posteo.de>
2023-09-01 23:23:03 +03:00
Cohee
1f10acdf17
Slight refactor Kobold version flags
2023-09-01 01:07:04 +03:00
Cohee
53f8667782
#1071 Initialize Ross mods only after the first load completed
2023-08-31 20:31:12 +03:00
Cohee
019c47adc6
#1068 Display token counts on generated messages
2023-08-31 17:10:01 +03:00
Cohee
05f3a5d8a1
#1041 Auto-fix displayed markdown for unbalanced quotes/asterisks
2023-08-31 14:39:31 +03:00
Cohee
c6bbbf1c25
Fix continue token count overflow
2023-08-31 00:16:58 +03:00
Cohee
10148167ba
Option to disable group impersonation ban. Hide CFG for simple UI
2023-08-30 16:31:53 +03:00
Cohee
7eebbca3dd
Fixed extension prompt insertion at depth 1
2023-08-30 02:09:30 +03:00
Cohee
44f88c61ff
Add simplified UI switch
2023-08-29 18:04:10 +03:00
Cohee
f60ddd6465
Fix group member reply trimming
2023-08-29 14:53:39 +03:00
Cohee
030424d034
Add char to persona converter. Move persona functions to a separate script file
2023-08-29 01:54:11 +03:00
Cohee
1bb2778f46
Fix macros replacement in custom stop strings for OAI
2023-08-29 00:47:35 +03:00
Cohee
9ce8aa661f
Deprecate "After Char" position for persona description
2023-08-29 00:10:18 +03:00
Cohee
3b4e6f0b78
Add debug functions menu
2023-08-27 23:20:43 +03:00
Cohee
8bf679cba2
#1033 Promt => prompt
2023-08-27 19:24:28 +03:00
Cohee
8ec9b64be4
Fix regeneration calls on empty chat
2023-08-27 13:34:29 +03:00
Stefan Daniel Schwarz
813a640334
Add model info to model icon as title
2023-08-27 12:13:55 +02:00
Cohee
0d8a83e6b6
Fix imported char flashing with pagination
2023-08-27 04:01:13 +03:00
Cohee
2685bf95fe
#1016 Pagination improvements
2023-08-27 02:13:46 +03:00
Stefan Daniel Schwarz
b9a95d94a0
Force isSystem = false on comment messages so they get formatted properly
2023-08-26 19:26:23 +02:00
Cohee
11c7c81d1b
Add template caching
2023-08-26 14:07:41 +03:00
Cohee
bca44ba682
Conserve ending newlines in story string template
2023-08-26 01:32:39 +03:00
Cohee
44661d0e2b
Merge branch 'staging' into generate-array
2023-08-26 01:07:19 +03:00
Cohee
fabba9370b
Merge pull request #1017 from StefanDanielSchwarz/improved-instruct-mode-sequences
...
improved instruct mode sequences and UI
2023-08-26 01:03:38 +03:00
SDS
45046aa211
Merge branch 'staging' into improved-instruct-mode-sequences
2023-08-25 23:06:44 +02:00
Stefan Daniel Schwarz
ddaa4fe409
force output sequence (first or last)
2023-08-25 22:02:11 +02:00
Stefan Daniel Schwarz
3ce3a7e6f1
Resolve conflicts
2023-08-25 21:07:10 +02:00
Stefan Daniel Schwarz
ca37ac679e
Improved Advanced Formatting UI
2023-08-25 21:04:06 +02:00
Cohee
cb669cbcab
Merge branch 'staging' of https://github.com/SillyTavern/SillyTavern into staging
2023-08-25 20:34:33 +03:00
Cohee
b32a085e41
Add template renderer for extensions
2023-08-25 20:34:26 +03:00
Cohee
12f1cdb3fd
#1020 Fix summarize + prompt manager. Clarify naming for insertion position.
2023-08-25 20:03:31 +03:00
Cohee
794abfcd6f
Disable swipe left when reply is still being generated.
2023-08-25 19:23:05 +03:00
Cohee
94d2b737e2
Fix OpenAI prompt injections + add type casts and typings on setting the extension prompt.
2023-08-25 17:05:51 +03:00
Cohee
d68151f7e2
Init author's note via function call instead of onready
2023-08-25 16:46:54 +03:00
Stefan Daniel Schwarz
be3ebcda0d
improved instruct mode sequences (WIP)
2023-08-25 14:01:25 +02:00
Cohee
c566af7695
#1014 Adjust group clean-up routine
2023-08-25 13:46:30 +03:00
Cohee
2cce6e83fa
Don't lose continued swipes
2023-08-25 01:27:27 +03:00
RossAscends
1a1878f095
Merge branch 'staging' of https://github.com/Cohee1207/SillyTavern into staging
2023-08-25 07:06:54 +09:00
RossAscends
ce5e706fac
topbar resize, font scaling fix, mobile slider fix
2023-08-25 07:06:52 +09:00
kingbri
1dd1607b94
Generate: Migrate to array-based message concatenation
...
String addition is very limited in how flexible it can be. Using
an array will instead allow for various ways to shift around extension
prompts and insertion depths.
To preserve message order, each mesSend object contains both a message
and an array of extension prompts which are later added on top of
the message itself.
Signed-off-by: kingbri <bdashore3@proton.me>
2023-08-24 18:02:17 -04:00
Cohee
1900ab9726
#1005 Replace mobile detection method in get sortable delay. Make deviceInfo loading sync. Init Ross mods via function call.
2023-08-24 23:52:03 +03:00
Cohee
c91ab3b5e0
Add Kobold tokenization to best match logic. Fix not being able to stop group chat regeneration
2023-08-24 21:23:35 +03:00
Cohee
f5fd15ffd2
#976 Return "Continue on send". Allow continuing the first chat message. Add debug function for i18n.
2023-08-24 15:13:04 +03:00
Cohee
3e25c3f51c
Merge pull request #1008 from mweldon/novel-generate-until-sentence
...
Novel generate until sentence
2023-08-24 11:25:56 +03:00
Cohee
d147bc40dc
Fix alternate greetings
2023-08-24 11:04:46 +03:00
Mike Weldon
8202fab376
Remove commented lines I added by mistake
2023-08-23 18:08:55 -07:00
Mike Weldon
1d1109e43b
Set generate_until_sentence for NovelAI
...
* Set generate_until_sentence true for NovelAI
* Add a Story String file for NovelAI with persona before character
which works better
* Remove hardcoded dinkus for chat_start since it is in the Story String
2023-08-23 18:04:56 -07:00
Cohee
ffc8150eef
Add missing space on continue
2023-08-24 02:38:02 +03:00
Cohee
4038e7f9e3
#999 Instruct mode fixes
2023-08-24 02:22:37 +03:00
Cohee
e2507e8840
#976 Add "quick continue" button. Remove "send to continue" option.
2023-08-24 01:37:44 +03:00
