2b3055a84a
Webp cards format is no longer supported
2023-09-15 14:56:15 +03:00
52891898d2
Pass max length to Kobold GUI settings
2023-09-14 18:20:12 +03:00
17a5d629ea
Auto-set hotswap slot number based on the screen width.
2023-09-14 15:56:01 +03:00
d62cdffcc0
Unblock amount_gen in Kobold GUI preset
2023-09-13 15:19:44 +03:00
bf0cf10403
Update hotswap state on fav
2023-09-13 13:12:19 +03:00
e74090139c
Add copy to clipboard button on prompt itemization popup ( #1124 )
...
* Add copy to clipboard button on prompt itemization popup
* Minor fix for NovelAI Summarize and new bad words
2023-09-13 11:52:37 +03:00
09fc42a787
Lock extensions display order in top and context menus
2023-09-13 01:40:01 +03:00
c0e5d7efae
Save chat scroll position when user input overflows the line
2023-09-13 00:51:21 +03:00
6c29879f12
Filter out undefined messages for past chats search
2023-09-12 18:05:37 +03:00
5cc6a2dca6
(WIP) Lazier chat loading
2023-09-11 01:07:45 +03:00
98cc969d18
Merge branch 'staging' into vectors
2023-09-10 16:06:15 +03:00
dc5deaf47c
Mobile doesn't like select2
2023-09-10 14:39:49 +03:00
0480acebcd
#1059 Mancer model selector
2023-09-10 04:08:32 +03:00
f8d90c1933
Merge branch 'staging' into vectors
2023-09-10 02:42:42 +03:00
3dbdd1258e
Don't close the panels when dismissing toasts
2023-09-10 02:30:23 +03:00
af38971a01
Delete vectors on deleting chats
2023-09-09 22:15:47 +03:00
31beb05aa1
Substitute macro in Novel preamble
2023-09-09 18:19:01 +03:00
4cf6a1f7da
Cache and sample classification results
2023-09-09 17:31:27 +03:00
da34517943
Merge branch 'staging' into vectors
2023-09-09 01:21:03 +03:00
ea01247bcf
#1090 Save Kobold/ooba servers history
2023-09-08 22:44:06 +03:00
6f3947226f
Merge pull request #1116 from ThisIsPIRI/macro
...
Replace macros in example separator and chat start
2023-09-08 21:10:20 +03:00
42fd317188
Merge branch 'staging' into vectors
2023-09-08 16:41:26 +03:00
2411b17279
Merge branch 'release' into staging
2023-09-08 16:40:45 +03:00
ab460199ab
#1117 Fix typing indicator and auto-scroll breaking mobile layout
2023-09-08 16:36:00 +03:00
2688d980c1
Replace macros in example separator and chat start
2023-09-08 19:25:17 +09:00
02bdd56e20
Make printMessages async
2023-09-08 12:10:41 +03:00
96df705409
Change insertion strategy to an extension block
2023-09-08 01:26:26 +03:00
f2cae64b0d
Added loop-around for swipe-left when multiple swipes exist ( #1104 )
...
* Added loop-around for swipe-left when multiple swipes exist
* Added loop around for alternate greetings in swipe_right(),
Disabled toast for add more alternate greetings
* Debounce saving swipes
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
2023-09-07 16:45:19 +03:00
853736fa93
Remove legacy NovelAI models
2023-09-06 14:32:06 +03:00
322511caa9
Remove legacy Pygmalion formatting, part 2
2023-09-06 14:19:29 +03:00
29124df66b
Merge branch 'staging' of https://github.com/SillyTavern/SillyTavern into staging
2023-09-06 14:07:04 +03:00
9c26e324ac
Remove legacy Pygmalion formatting
2023-09-06 14:07:00 +03:00
889a1b5323
Fixed multiple zoomed avatars from appearing. Excluding moving UI ( #1098 )
...
* Fixed multiple zoomed avatars from appearing
* Added check for moving UI elements
2023-09-05 21:40:22 +03:00
bbed147ce5
Clean up browser logs
2023-09-05 18:23:24 +03:00
7b3f242454
Merge pull request #1094 from GanstaKingofSA/staging
...
Improved cleanup for Instruct Mode
2023-09-05 10:57:48 +03:00
ab8fb98f5d
fix zoomed avatars when swapping personas
2023-09-05 10:09:35 +09:00
5d0a4fa940
add input sequence as stop sequence by default
2023-09-04 16:29:49 -05:00
8636987d8a
Merge pull request #1091 from city-unit/feature/chub
2023-09-04 20:15:41 +03:00
01e38be408
Expose importing dropped images for consistent import
2023-09-04 13:09:47 -04:00
ded1e3a859
Add NAI Diffusion upscaling. Add Anlas guard and view Anlas button
2023-09-04 18:00:15 +03:00
e616ab5ced
Don't subtract WI tokens from ChatCompts prompt itemization
2023-09-04 14:31:00 +03:00
c110ebe02b
Fix chat bg gens not saving. Remove module worker pattern and global function from chat bg plugin
2023-09-04 12:18:37 +03:00
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
1f10acdf17
Slight refactor Kobold version flags
2023-09-01 01:07:04 +03:00
53f8667782
#1071 Initialize Ross mods only after the first load completed
2023-08-31 20:31:12 +03:00
019c47adc6
#1068 Display token counts on generated messages
2023-08-31 17:10:01 +03:00
05f3a5d8a1
#1041 Auto-fix displayed markdown for unbalanced quotes/asterisks
2023-08-31 14:39:31 +03:00
c6bbbf1c25
Fix continue token count overflow
2023-08-31 00:16:58 +03:00
10148167ba
Option to disable group impersonation ban. Hide CFG for simple UI
2023-08-30 16:31:53 +03:00
7eebbca3dd
Fixed extension prompt insertion at depth 1
2023-08-30 02:09:30 +03:00
44f88c61ff
Add simplified UI switch
2023-08-29 18:04:10 +03:00
f60ddd6465
Fix group member reply trimming
2023-08-29 14:53:39 +03:00
030424d034
Add char to persona converter. Move persona functions to a separate script file
2023-08-29 01:54:11 +03:00
1bb2778f46
Fix macros replacement in custom stop strings for OAI
2023-08-29 00:47:35 +03:00
9ce8aa661f
Deprecate "After Char" position for persona description
2023-08-29 00:10:18 +03:00
3b4e6f0b78
Add debug functions menu
2023-08-27 23:20:43 +03:00
8bf679cba2
#1033 Promt => prompt
2023-08-27 19:24:28 +03:00
8ec9b64be4
Fix regeneration calls on empty chat
2023-08-27 13:34:29 +03:00
813a640334
Add model info to model icon as title
2023-08-27 12:13:55 +02:00
0d8a83e6b6
Fix imported char flashing with pagination
2023-08-27 04:01:13 +03:00
2685bf95fe
#1016 Pagination improvements
2023-08-27 02:13:46 +03:00
b9a95d94a0
Force isSystem = false on comment messages so they get formatted properly
2023-08-26 19:26:23 +02:00
11c7c81d1b
Add template caching
2023-08-26 14:07:41 +03:00
bca44ba682
Conserve ending newlines in story string template
2023-08-26 01:32:39 +03:00
44661d0e2b
Merge branch 'staging' into generate-array
2023-08-26 01:07:19 +03:00
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
45046aa211
Merge branch 'staging' into improved-instruct-mode-sequences
2023-08-25 23:06:44 +02:00
ddaa4fe409
force output sequence (first or last)
2023-08-25 22:02:11 +02:00
3ce3a7e6f1
Resolve conflicts
2023-08-25 21:07:10 +02:00
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
2615eb8532
Extract system message templates to template files
2023-08-22 10:37:18 +03:00
ecfe8a722f
Generate: Fix prompt bias addition
...
If the bias is empty, don't add it.
Signed-off-by: kingbri <bdashore3@proton.me>
2023-08-21 23:54:53 -04:00
d974866ed7
Fix missing space in ST version string
2023-08-22 00:40:39 +03:00
57b126bfbf
Save chat completions settings to an object. Update numeric setting types
2023-08-22 00:35:46 +03:00
07d7eb733d
Fix raw prompts display in prompt itemizer
2023-08-21 23:50:38 +03:00
069a07a139
Add pagination for WI entries #964
2023-08-21 21:10:11 +03:00
05d719107f
Move total token counter. Tighten the UI
2023-08-21 17:00:28 +03:00
c735bf546a
Add token counters for individual fields. Optimize total counter display
2023-08-21 15:32:27 +03:00
60faaf1831
CFG: NAI fixes
...
NAI does CFG differently, so add special cases for them. Also gate
CFG access to only work on textgenwebui since that's where it's
implemented.
Signed-off-by: kingbri <bdashore3@proton.me>
2023-08-20 19:58:17 -04:00
4ea9e481a8
Merge branch 'staging' into staging
2023-08-21 01:51:12 +03:00
ad2be21531
Generate: Fix appends on continue
...
Continue was in a semi-working state. However, the generated prompt
by continue was a mess and didn't remove essential parts such as
character name and prompt bias. This caused duplication and bad
generations.
Now, append the prompt bias after the CFG has been appended and then
clean up the continued cache before adding it to the final prompt.
Signed-off-by: kingbri <bdashore3@proton.me>
2023-08-20 17:36:35 -04:00
8bb59a9e22
Merge branch 'staging' of https://github.com/SillyTavern/SillyTavern into staging
2023-08-20 23:33:26 +03:00
6738ffe2a4
Add auto-select for instruct presets. Re-organize instruct mode code. Prepare for preset manager integration
2023-08-20 23:29:43 +03:00
013a0a56b4
Merge pull request #983 from StefanDanielSchwarz/simple-proxy-for-tavern-replacement-enhanced
...
Simple proxy for tavern replacement enhanced
2023-08-20 23:27:33 +03:00
f5d5b2f749
Format instruct mode examples
2023-08-20 22:03:45 +02:00
d02fa88d3a
Comment-out bookmark validation
2023-08-20 19:43:58 +03:00
6e6eb8f61e
Use CSS class for coloring
2023-08-20 19:09:19 +03:00
a27bef8b12
Merge branch 'staging' into qolfeatures
2023-08-20 18:47:43 +03:00
2ff2973d2b
Instruct system prompt for instruct mode only
2023-08-20 17:30:19 +02:00
2fb86c8ebd
Added Persona Description and System Prompt to Story String
2023-08-20 16:08:54 +02:00
6fb278266b
Merge pull request #977 from city-unit/feature/exorcism
...
Feature/exorcism
2023-08-20 12:37:56 +03:00
94754af013
Reformat code
2023-08-20 12:37:38 +03:00
84e5a63c34
Fix SD group gen bugs
2023-08-20 12:29:20 +03:00
ac319dbd30
CFG: Add positive prompt support and fixes
...
Positive prompts are the opposite of negative prompts. This helps
make the mixing process more accurate by keeping the negative differences
as close as possible to the positive ones by including this prompt.
In addition, fix prompt insertion order at a depth of 0 by hijacking
the same function used for Author's Note as a zero depth anchor.
Signed-off-by: kingbri <bdashore3@proton.me>
2023-08-20 02:22:23 -04:00
92e6c6a998
CFG: Use ST prompt builder for negatives
...
Make the generate function build a negative prompt in addition to the
normal one. This allows for nonconflicting insertion with other extension
prompts and World Info.
Signed-off-by: kingbri <bdashore3@proton.me>
2023-08-20 00:44:39 -04:00
8dca75f6c3
single-URL ui for mancer.
...
automatically produce streaming URL from blocking URL.
2023-08-20 00:33:00 -04:00
e76001a600
Merge branch 'staging' of https://github.com/city-unit/SillyTavern into feature/exorcism
2023-08-19 23:58:11 -04:00
2f09efcd7f
Exorcised base64 image stuff
2023-08-19 23:01:09 -04:00
674228a5f5
Fix character JB / prompt + Original
2023-08-19 21:36:22 +03:00
5cecc9fbff
Scrub proxy from exported presets
...
Speed-up animations.
2023-08-19 21:13:37 +03:00
e0de442523
Merge branch 'staging' of https://github.com/Cohee1207/SillyTavern into qolfeatures
2023-08-20 03:22:54 +10:00
771c9d6165
Optimize SVG loader. Add ai21 icon
2023-08-19 19:48:33 +03:00
dba685bffb
Added detection for broken/deleted bookmark links, can expand on this to automatically delete broken links, but for now it just hides the icon.
2023-08-20 02:45:20 +10:00
b56fe3e01b
Made favorite characters/groups more apparent
2023-08-20 02:30:57 +10:00
0d694dcc32
Added power user option to remove examples
2023-08-20 02:25:07 +10:00
a4f075a9b1
Added swipe deletion
2023-08-20 02:11:45 +10:00
438c78574f
Merge pull request #971 from kingbased/jurassic
...
AI21 Adapter
2023-08-19 18:48:15 +03:00
0f21eabb6e
AI21 Adapter + Tokenization implementation
2023-08-20 01:20:42 +10:00
336e27a92d
Move 3rd-party scripts into /lib
2023-08-19 16:29:46 +03:00
2d61c9954b
Pagination tweaks
2023-08-19 16:11:09 +03:00
991ff98eaa
Performance optimizations for character edit / chat opening
2023-08-19 15:58:17 +03:00
3acd0a590e
Merge pull request #966 from StefanDanielSchwarz/simple-proxy-for-tavern-replacement
...
Simple proxy for tavern replacement
2023-08-19 14:35:43 +03:00
7191f7a8ad
CFG: Add insertion depth and custom separator
...
Insertion depth allows for CFG to variably inject itself into the
negative prompt. This is similar to how Author's note works.
However, this method of insertion depth conflicts with AN and
world info where negatives can be meshed between two lines
of those specific insertions.
A custom separator must be wrapped in quotes, otherwise the default
separator is a newline for negative cascading.
Signed-off-by: kingbri <bdashore3@proton.me>
2023-08-19 01:29:59 -04:00
8581ef14dd
Add search filtering for past chats
2023-08-18 23:48:08 -04:00
4488cee65d
Add search filtering for past chats
2023-08-18 23:45:05 -04:00
cdbca6d9fd
CFG: Include the entire prompt with negative prompt
...
CFG with LLMs works differently than stable diffusion. The main principle
is prompt mixing and utilizing the differences between the two prompts
rather than a full "negative prompt" of what the user doesn't want.
SillyTavern its own way of formatting a prompt sent to an LLM backend.
Therefore, take that prompt and add negatives to it.
Signed-off-by: kingbri <bdashore3@proton.me>
2023-08-18 22:18:09 -04:00
059647b286
Dynamically update group avatars
2023-08-19 03:13:40 +03:00
f27107e0ef
Refactor and optimize group members display
2023-08-19 02:53:05 +03:00
bcc66de1df
multi-line clean-up message
2023-08-18 23:28:11 +02:00
599a912a5a
deduplicated multi-line stopping strings
2023-08-18 23:02:59 +02:00
602c5cd791
Add pagination for characters list view
2023-08-18 23:13:15 +03:00
7e5d08874f
Handle last_output_sequence like output_sequence
2023-08-18 21:18:27 +02:00
0c5c8c50ad
half-fix for small boxes in mobile no spoiler view
2023-08-18 22:45:40 +09:00
5528a493a6
Do not insert an extra newline if example separator is empty
2023-08-18 12:32:52 +03:00
75378eff4e
#937 Add dynamic chat backgrounds generation
2023-08-18 00:41:21 +03:00
80092b3170
#790 Simplify local prompt formatting. Use handlebars to render story string.
2023-08-17 22:47:34 +03:00
86a486be8f
Adjust Novel instruction prompts for quiet generation
2023-08-17 17:40:38 +03:00
928d897946
Fix instruct mode stop strings for whitespace sequences
2023-08-17 11:47:15 +03:00
7a204bef05
Show chat completion source on hover
2023-08-16 13:51:38 +03:00
4a0c93f023
Show OpenRouter icon
2023-08-15 21:36:28 +03:00
2afac5aeb1
Filter null messages in array and context line appearing unprompted
2023-08-15 15:08:42 +03:00
41ec7e5600
Many NovelAI fixes from dev guidance
...
* Remove AI Module "Autoselect" and make the auto-instruct work for all modules. This is how NAI is supposed to work.
* Log the response from the API.
* Move the AI Module setting up to the top of the settings window since it isn't part of the preset.
* Refactor phrase_rep_pen to use the actual API strings.
* Clamp the maximum token length to 150 before we call the API.
* Clamp the minimum token length in the UX from 1 to 150.
* Fix bug where the preamble was not initialized on cold start.
* Get rid of extra newline before dinkus.
* Make always_force_name2 default true.
2023-08-14 19:35:21 -07:00
a92333875c
Try to minimize side effects of generate dry running
2023-08-15 00:01:55 +03:00
15db16ee8d
Fuzzy search for groups
2023-08-14 17:35:48 +03:00
bd9f49d975
Don't launch generation intercepts on dry runs
2023-08-14 11:43:31 +03:00
c86512cf6b
Fix swiping
2023-08-13 22:57:49 -04:00
f528791c4f
Merge branch 'staging' of https://github.com/city-unit/SillyTavern into feature/ui
2023-08-13 18:46:37 -04:00
ad04344392
Api/Model icon option
2023-08-13 18:43:16 -04:00
c0bc425c8b
Debounce manager changes
2023-08-13 18:43:17 +03:00
9615495878
Merge pull request #768 from SillyTavern/prompt-manager-cherrypicked
...
Feature: Prompt manager (cherrypicked onto stage)
2023-08-13 14:44:28 +03:00
f434a96ad6
fix double import on char card drop
2023-08-13 01:47:33 +09:00
b1254fa2ab
Copy migrated preset into loaded presets
...
Since this only is populated once during page load
2023-08-12 18:40:39 +02:00
2805a684a8
Emit events on changing chatcompletion source or model
2023-08-12 18:40:39 +02:00
d9e7eba617
Emit event when a single chat message is deleted
2023-08-12 18:40:39 +02:00
fd10eaf037
Close and clear popup on preset change
2023-08-12 18:40:39 +02:00
af81915ff3
Update existing prompts during migration
...
Instead of adding new prompts for main, jailbreak and nsfw
2023-08-12 18:40:39 +02:00
63d224d8af
Refactor and simplify setup method for prompt manager.
2023-08-12 18:40:39 +02:00
ec806db9f7
Initialize prompt manager on selecting openrouter, scale
2023-08-12 18:40:39 +02:00
4dd94a4a62
Do not generate group responses on dry run
2023-08-12 18:40:39 +02:00
4974c81d4c
Update prompt manager active character on character edit.
2023-08-12 18:40:38 +02:00
74a7aa513b
Reintroduce event types after rebase
2023-08-12 18:40:38 +02:00
579f303fb0
Add event for modifying settings before modifications
2023-08-12 18:40:38 +02:00
550e635d93
Add migration for legacy prompts
2023-08-12 18:40:38 +02:00
e908610b99
Save prompt manager items to perset
2023-08-12 18:40:38 +02:00
6cea524f2c
Fix prompt-manager being rendered twice.
2023-08-12 18:40:38 +02:00
7c1e370abe
Allow the user to toggle names in chat history
2023-08-12 18:40:38 +02:00
f207e0eab3
Add basic WindowAI support
2023-08-12 18:40:38 +02:00
aaa2c48e7d
Add basic claude support
2023-08-12 18:40:38 +02:00
6e37db2fb3
Declare prepareOpenAIMessages as synchronous
...
As there is no need for the function o be async anymore.
2023-08-12 18:40:38 +02:00
77e183f5dd
Add support for authors note and summary extensions
2023-08-12 18:40:18 +02:00
eb315993b4
Let prompt manager handle character and scenario prompts
2023-08-12 18:40:18 +02:00
c92de398b9
Fire event after a chat has successfully loaded
2023-08-12 18:40:18 +02:00
b8d08161ab
Allow generate to run without sending a request
2023-08-12 18:40:18 +02:00
3acd865bf8
Introduce new substitute parameters
...
charIfNotGroup and group
2023-08-12 18:40:18 +02:00
a5e2f11e61
Use EventEmitter instead of native event handling
2023-08-12 18:40:18 +02:00
63985a490d
Add error handling to parseTokenCounts function
2023-08-12 18:40:17 +02:00
c6eee88cd4
Add prompt manager setup
2023-08-12 18:39:54 +02:00
092846e0bc
#924 Replace Novel Kayra subtier context
2023-08-12 14:21:05 +03:00
82f6d11795
Add lazy chat messages rendering
2023-08-12 13:10:50 +03:00
9e43f5f8b7
Add flat budget cap for hybrid WI budgeting
2023-08-10 20:45:57 +03:00
104d983449
Adjust novel max context calculation
2023-08-10 19:15:52 +03:00
f226fe99aa
Showdown render tables
2023-08-10 13:18:12 +03:00
1a07fa8365
[Feature Request] Can we please have <xml_tags> visibility back? #907
2023-08-10 11:47:17 +03:00
e39e9428b6
Allow incomplete sentences on quiet prompts
2023-08-09 16:41:12 +03:00
0ed340bd9a
Merge pull request #901 from 50h100a/mancer-urlfix
...
Relax URL requirements when Mancer is enabled.
2023-08-08 23:27:05 +03:00
53e41bdda8
Relax URL requirements when Mancer is enabled.
2023-08-08 16:12:03 -04:00
cd86999d30
Fix variable name
2023-08-08 22:39:34 +03:00
2fea218661
Extend random and roll syntax for frontend compatibility
2023-08-08 22:36:42 +03:00
ef3a9a810e
Fix avatar preview after changing it
2023-08-08 22:08:41 +03:00
78825352e5
more help format updates
2023-08-08 18:03:39 +09:00
264b52b52d
update help format
2023-08-08 17:42:28 +09:00
c124fc589f
Fix display help links
2023-08-07 22:21:10 +03:00
f8e8929834
Merge pull request #896 from majick/tiny-cosmetic
2023-08-07 19:53:35 +03:00
4167047f9b
Cosmetic: The avatar crop accept button is labeled "Accept"
2023-08-07 09:49:07 -07:00
e0d6430ade
Fix copy-paste issue
2023-08-07 02:20:53 +03:00
23a57e86a7
Try to remove excess character names from generations
2023-08-07 00:31:26 +03:00
151f4d322c
#883 Add option to disable CSRF tokens
2023-08-06 16:42:15 +03:00
cfc4394e41
Resolve some API Spam / Fix 1 Token for 0 Token Counters
2023-08-06 05:58:26 +01:00
ef1f6b3143
Merge branch 'staging' of https://github.com/SillyLossy/TavernAI into staging
2023-08-05 15:44:18 +03:00
58f7c77281
Reformat code
2023-08-05 15:44:15 +03:00
6ddfcc7a06
Enable quote blocks and HTML comments
2023-08-05 12:29:37 +03:00
b407fe2388
custom_stopping_strings_macro toggleable option
2023-08-04 16:53:49 +02:00
33af7ad266
Replace Macro in Custom Stopping Strings
...
Replaces user and char names in custom stopping strings, making them much more versatile and useful.
Example Use Case: Now you can use a custom stopping string like "\n*{{user}} " to stop generation when the AI tries to act as the user.
2023-08-04 15:45:45 +02:00
cd8a24a712
Fix bulk edit
2023-08-04 14:41:00 +03:00
84283bc2b4
Add "Best match" tokenizer option
2023-08-04 14:17:05 +03:00
079b1623c5
NovelAI preamble code cleanup
2023-08-03 18:27:23 -07:00
ea809023b5
Merge pull request #858 from 50h100a/mancer-api
...
Mancer API
2023-08-03 23:06:53 +03:00
65732f4406
del_char_checkbox unchecked by default
...
When you delete a character, you can always re-import them - but if you deleted the chat files, they're gone forever unless you backed them up manually. That's why I think this checkbox should be off by default, making chat file deletion a conscious effort.
With it off, worst case someone forgets to check the box and has some unnecessary files on their disk that they can then delete manually. That's much less of a problem than someone forgetting to uncheck the box (e. g. when importing a new version of the character) and then suffering data loss.
2023-08-03 15:39:15 +02:00
9cf4056b28
Do backflips trying to get error information from endpoints.
...
Then present it nicely.
2023-08-03 07:32:53 -04:00
37e653dcf4
Add toggle for persona info notifications
2023-08-03 14:24:45 +03:00
2fc6813e66
code review adjustments part 1
2023-08-03 06:07:54 -04:00
Cohee
mweldon
ThisIsPIRI
anmelus
RossAscends
GanstaKingofSA
city-unit
Stefan Daniel Schwarz
SDS
kingbri
maver
50h100a
based
Cohee1207
majick
AeonBlack