ca37ac679e
Improved Advanced Formatting UI
2023-08-25 21:04:06 +02:00
cb669cbcab
Merge branch 'staging' of https://github.com/SillyTavern/SillyTavern into staging
2023-08-25 20:34:33 +03:00
b32a085e41
Add template renderer for extensions
2023-08-25 20:34:26 +03:00
12f1cdb3fd
#1020 Fix summarize + prompt manager. Clarify naming for insertion position.
2023-08-25 20:03:31 +03:00
794abfcd6f
Disable swipe left when reply is still being generated.
2023-08-25 19:23:05 +03:00
94d2b737e2
Fix OpenAI prompt injections + add type casts and typings on setting the extension prompt.
2023-08-25 17:05:51 +03:00
d68151f7e2
Init author's note via function call instead of onready
2023-08-25 16:46:54 +03:00
be3ebcda0d
improved instruct mode sequences (WIP)
2023-08-25 14:01:25 +02:00
c566af7695
#1014 Adjust group clean-up routine
2023-08-25 13:46:30 +03:00
2cce6e83fa
Don't lose continued swipes
2023-08-25 01:27:27 +03:00
1a1878f095
Merge branch 'staging' of https://github.com/Cohee1207/SillyTavern into staging
2023-08-25 07:06:54 +09:00
ce5e706fac
topbar resize, font scaling fix, mobile slider fix
2023-08-25 07:06:52 +09:00
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
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
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
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
3e25c3f51c
Merge pull request #1008 from mweldon/novel-generate-until-sentence
...
Novel generate until sentence
2023-08-24 11:25:56 +03:00
d147bc40dc
Fix alternate greetings
2023-08-24 11:04:46 +03:00
8202fab376
Remove commented lines I added by mistake
2023-08-23 18:08:55 -07:00
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
ffc8150eef
Add missing space on continue
2023-08-24 02:38:02 +03:00
4038e7f9e3
#999 Instruct mode fixes
2023-08-24 02:22:37 +03:00
e2507e8840
#976 Add "quick continue" button. Remove "send to continue" option.
2023-08-24 01:37:44 +03:00
d64c5880c8
Fix new chat reference not getting saved when starting a new chat
2023-08-24 00:54:36 +03:00
de0dbfb394
Merge branch 'roleplay-context' into staging
2023-08-24 00:30:04 +03:00
1ce848c1c3
Move before / after char WI to story strings
2023-08-24 00:26:47 +03:00
9aa03402fa
Merge pull request #1004 from SillyTavern/prompt-manager-persona-description
...
Prompt manager persona description
2023-08-23 22:11:47 +03:00
5a02250a1f
Add persona description to prompt manager order
2023-08-23 20:40:26 +02:00
632d03228f
Merge branch 'staging' of https://github.com/Cohee1207/SillyTavern into staging
2023-08-24 03:34:25 +09:00
6c56fb0a6d
500ms delay for sliders on touch devices
2023-08-24 03:34:20 +09:00
1d6b7c9947
Merge branch 'staging' of https://github.com/SillyTavern/SillyTavern into staging
2023-08-23 21:32:46 +03:00
031a6cb2a4
Performance and data integrity improvements
2023-08-23 21:32:38 +03:00
2c58f9d903
Merge pull request #1001 from bdashore3/staging
...
More CFG fixes
2023-08-23 18:49:36 +03:00
0460375647
CFG: Don't inject anything when guidance scale doesn't exist
...
If the guidance scale is 1, completely disable sending CFG and creating
a negative prompt.
Signed-off-by: kingbri <bdashore3@proton.me >
2023-08-23 11:27:58 -04:00
f48cc0db31
Unify cfgValues parsing between ooba/Novel
2023-08-23 18:26:56 +03:00
2c2a68ef76
Fix instruct system sequence missing + {{original}}
2023-08-23 18:04:22 +03:00
b751643364
Save pagination state on return to list from card
2023-08-23 16:48:44 +03:00
e77da62b85
Add padding to cache key. Fix Safari display issues. Fix 400 on empty translate. Reset bias cache on changing model.
2023-08-23 10:32:48 +03:00
bc5fc67906
Put tokenizer functions to a separate file. Cache local models token counts
2023-08-23 02:38:43 +03:00
fd95b79ae9
Fix auto-translate plugin. Add new event types for post-rendering
2023-08-22 22:45:12 +03:00
16406f2698
Fix Chat Completions itemization
2023-08-22 20:34:20 +03:00
38a08cd887
Merge pull request #968 from bdashore3/staging
...
CFG: Improvements
2023-08-22 19:00:39 +03:00
042c0b84a1
Add a token counter for persona descriptions
2023-08-22 18:32:18 +03:00
ea4d4a8fd6
Fix system messages using incorrect timezone
2023-08-22 18:13:03 +03:00
41cc86af9f
Add example extension for chat variables. Allow registering custom text processing functions for extensions
2023-08-22 17:46:37 +03:00
25c7686462
CFG: Pass entire guidance object
...
If an API doesn't use the negative prompt from generate, allow
the negative prompt to be refetched in the specific API. This
requires the full guidance scale object instead of just the number.
Signed-off-by: kingbri <bdashore3@proton.me >
2023-08-22 10:17:20 -04:00
1abb739a8c
Replace one-time bias regex parser with Handlebars helper
2023-08-22 16:14:21 +03:00
c7ce6a4953
Move prompt itemization to HTML templates
2023-08-22 14:50:43 +03:00
9deaec5877
More typechecks and comments
2023-08-22 14:30:49 +03:00
e2bac7ec5f
Add type checking and JSDoc comments to some utils
2023-08-22 13:07:24 +03:00
