Commit Graph

1520 Commits

Author SHA1 Message Date
bfda5a5492 Extra fixes (#1185) 2023-09-26 09:53:04 +03:00
edb79d8c53 Synchronize max depths for plugins 2023-09-25 19:29:24 +03:00
423f88a458 Skill issue 2023-09-24 15:04:02 +03:00
1838ca1994 Replace magic numbers with named constants 2023-09-24 14:45:04 +03:00
2411006fdb World Info: Add insertion order at depth (#1174)
Depth previously injected entries randomly. This is not ideal for
world info architectures that rely on insertion order to function
properly.

Redo depth injection to have its own parameter and redo how it's
handled in generate.

Signed-off-by: kingbri <bdashore3@proton.me>
2023-09-24 14:41:56 +03:00
a081f78bd8 (WIP) PaLM API 2023-09-23 20:48:56 +03:00
3d1312c13a Restyle chat width slider 2023-09-22 16:56:01 +03:00
ae4a9a7b14 Remove legacy chat lazy load 2023-09-21 22:07:56 +03:00
6ae1b7a72b Filter out "undefined" stopping strings 2023-09-21 22:02:51 +03:00
902acc44a2 Support "before main prompt" extension position in prompt manager 2023-09-21 20:46:08 +03:00
86c7a7a058 @Depth insertion for WI Entries 2023-09-21 16:04:34 +09:00
e0b5df97c4 Add branching as distinct from bookmarking 2023-09-20 22:48:05 -04:00
b52f71dcce Vectors: Add before story string/prompt option
This makes the most sense for placement of memories. Add the functionality
for other extension prompt placements as well.

Signed-off-by: kingbri <bdashore3@proton.me>
2023-09-20 00:06:43 -04:00
3a8383ab79 Append continue message timer instead of rewriting 2023-09-18 02:12:06 +03:00
0033090a93 Idle Response / Continuous Generation (#1132)
* Initial idle stuff

* Much closer, can now quietly send as user to get a char response.

* Tweaks

* Better, reset the count of getting a message back, don't send while prompt is waiting.

* Allow selecting who is being prompted

* Comments and cleaup

* Remove char name for the moment (needs something here probably)

* Add random time period and "Always add character's name to prompt" respect

* Tooltips

* Load/unload listeners

* Reduce log spam

* Add inline prompt inclusion

* Add full loud prompting

* Comments

* Fix instruct newline (I think)

* Don't reset count on continue

* add quietToLoud for script.js

* add quietToLoud for slashcommands.js

* Keep instruct directives

* Removed some logging, don't do the Novel formatting if Q2L

* Logspam begone.

* Removed a bit more logging

* Add alignment style

* Reformat files. Add comments

* Reorder extensions

* Fix repeat logic to prompt once then only repeat the number specified

* Make repeat count more clear

---------

Co-authored-by: RossAscends <124905043+RossAscends@users.noreply.github.com>
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
2023-09-17 22:00:10 +03:00
d861c59f27 Merge branch 'release' into staging 2023-09-17 16:11:27 +03:00
23b08173ff Asynchronously fetch chats 2023-09-17 13:41:36 +08:00
9f15e67856 make zoomed avatars detectable by Escape hotkey 2023-09-17 05:17:02 +09:00
38b63b07f5 Extract sprite and custom content endpoints to a separate files. Update constants references 2023-09-16 17:28:28 +03:00
6e562bd1ff Extract server endpoints for thumbnails and extensions into separate files 2023-09-16 16:16:48 +03:00
57de6229f9 Merge branch 'staging' of https://github.com/Cohee1207/SillyTavern into staging 2023-09-16 12:50:11 +09:00
e162df67fa partially fix quietPrompts (/sysgen) for Instruct 2023-09-16 12:48:14 +09:00
dae09d58d7 Fix scroll top offset for new import flashing 2023-09-16 00:46:27 +03:00
6dd09858d4 Don't remove names from the past chat. Fix non-streaming auto-continue.
We took fair criticism from the NovelAI dev.
2023-09-15 23:32:01 +03:00
fc7a4538e9 Cancel auto-continue if user input is not empty 2023-09-15 22:26:53 +03:00
77c8bc8eb5 Don't trigger auto-continue after quiet gens 2023-09-15 21:49:52 +03:00
d34f7d3e1a Replace multigen with auto-continue 2023-09-15 21:34:41 +03:00
599904d589 Move NovelAI endpoints to separate file 2023-09-15 17:54:13 +03:00
0f1a0963fd Merge branch 'release' into staging 2023-09-15 15:06:13 +03:00
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