Cohee
532418c534
Lint fixes
2024-03-17 14:07:33 +02:00
Cohee
ad450981c0
Fix unfocusing tag input when switching characters
2024-03-16 23:35:41 +02:00
Cohee
a789c6f76f
Format fix
2024-03-16 23:20:35 +02:00
Cohee
77784585ba
Merge branch 'staging' into tags-as-folders-enhancements
2024-03-16 22:32:01 +02:00
Cohee
3ed7ccbc57
Fix double rendering of first message when opening a chat with only 1 message
2024-03-16 18:22:33 +02:00
Cohee
2173b8b22a
Add event tracing debug function
2024-03-16 18:17:04 +02:00
Cohee
7aa5ab2d8d
Fix performance of loading very large chats
2024-03-16 02:19:41 +02:00
Cohee
a12793a9ac
Lazy evaluation of macro in first message
2024-03-15 11:39:21 +02:00
Cohee
ce756bc4f7
Allow setting altering group greetings with extensions. Add ability to add extensions when creating characters.
2024-03-14 23:10:35 +02:00
Cohee
acf36b6107
Add koboldcpp API key/password support
2024-03-14 00:34:09 +02:00
Deciare
be74f0a6d1
Fix Continue operation when jailbreak enabled.
...
When character jailbreak prompt is enabled for the text generation API,
the jailbreak prompt was always inserted as the last message in history,
so the Continue operation was completing the jailbreak prompt instead of
the character's last output.
2024-03-12 20:07:40 -04:00
Cohee
7ad2473f99
Add char.card Jailbreak support for Text Completion APIs
2024-03-12 23:22:29 +02:00
Cohee
6b2374c405
Add function to write extension fields to character cards.
2024-03-12 01:49:05 +02:00
Cohee
de3039977c
Fix substituteParams JSDoc
2024-03-10 00:52:39 +02:00
Cohee
73fdcbad44
Fix some bugs (see below):
...
1. Remove yellow highlights in hotswaps list.
2. Decrease font size of group members list, make it respect the block limits (1 row for small avatars, 3 rows for big avatars).
3. Fix autoload loading the first character if the latest selected entity was a group.
4. Fix tag key potentially skipping the first character.
5. Fix being unable to open groups from the hotswaps panel.
6. Fix left alignment of hotswaps panel, now centered.
7. Fix rounding of missing group avatars (most noticeable when favorited).
2024-03-09 21:58:13 +02:00
Cohee
32049b7e1d
Merge branch 'staging' into tags-as-folders-enhancements
2024-03-09 21:15:13 +02:00
Cohee
cdbb979a3e
Merge pull request #1909 from ThisIsPIRI/unlock
...
Prevent presets without a max context/response value from unchecking unlocked context
2024-03-09 21:14:00 +02:00
Cohee
26c0886856
Placeholder for Pygmalion character source
2024-03-09 21:10:20 +02:00
ThisIsPIRI
535126083e
Prevent presets without a max context/response value from unchecking unlocked context
2024-03-08 17:12:53 +09:00
Wolfsblvt
5ac7826fec
Tag Folders: Additional Fixes
...
- Refactored to one general printTagList method
- Made a robust getTagKeyForEntity function
- Fixed group not displaying tags if autoloaded
- Fixed added tags on character/groups not being auto sorted
- Fixed autoload of group/character that I killed
- Fixed typo
2024-03-07 23:48:50 +01:00
Wolfsblvt
7b49290fec
Merge branch 'staging' into tags-as-folders-enhancements
2024-03-07 16:09:57 +01:00
DreamGenX
5c410986a4
Add support for DreamGen API.
...
API docs: https://dreamgen.com/docs/models/opus/v1
API keys: https://dreamgen.com/account/api-keys
I decided to base this on the text-completion API since it's more
flexible with SillyTavern's prompt formating capabilities.
This also means that custom context and instruct settings are required.
Will add documentation in a followup PR.
2024-03-07 12:25:48 +01:00
Wolfsblvt
fb97f563b7
Tag Folders: show hidden numbers
...
- Show hidden counts for folders, and total
- Rework resizing of character names to shrink additional data first
- Better placement for group numbers
2024-03-07 02:15:41 +01:00
Wolfsblvt
18379ec602
Tag Folders: Improve global tag filters
...
- Update global tag filters to three-state filters
- Add filter for folders (showing empty folders or no folders)
- Final fix of filtering (should be correct now)
2024-03-06 23:13:22 +01:00
Cohee
66a926c8c7
Disable imports and char.creation while generating
...
This could cause data corruption due to active char Id being shifted.
2024-03-06 21:29:00 +02:00
Wolfsblvt
fc6146fa00
Tag Folders: Rework favorites display
...
- Favorites display uses same method than inline avatars
- Favorites now respect avatar style
2024-03-06 04:59:39 +01:00
Wolfsblvt
8e184254c8
Merge branch 'staging' into tags-as-folders-enhancements
2024-03-06 01:07:22 +01:00
Wolfsblvt
4ab45330c4
Tag Folders: Refactor tag code into tag.js
2024-03-06 01:05:08 +01:00
Wolfsblvt
e578d3dbb6
Tag Folders: hidden/closed folders
...
- Implement folder types: Open, Closed, None
- Closed folders hide characters from most places
- "character(s)" singular wording on entity list
- small refactoring for that code
2024-03-06 00:28:14 +01:00
Cohee
dc32884ced
#1891 Fix JWT Scale generation
2024-03-04 22:24:50 +02:00
Cohee
24b33a5f77
Add option for inline character card replacements
2024-03-03 21:04:27 +02:00
Cohee
c4cae9d00f
Refactor source, add confirm
2024-03-03 20:29:34 +02:00
Cohee
2e002032b3
Merge pull request #1882 from berbant/staging
...
Link to character's source page
2024-03-03 20:24:51 +02:00
Cohee
23c2a0d8f5
Fix card fields replace if missing
2024-03-03 18:56:05 +02:00
Cohee
8767c2a90b
Respect external media preferences in creator notes
2024-03-03 16:57:38 +02:00
Cohee
8cf1671d56
Sanitize creator's notes
2024-03-03 16:49:44 +02:00
Cohee
8ee0348a01
Merge branch 'import-uuid' into staging
2024-03-03 16:46:35 +02:00
Cohee
1395f9bd9e
Merge pull request #1887 from Bronya-Rand/staging
...
Import PygmalionAI/JanitorAI/Chub Bots via UUID
2024-03-03 16:46:22 +02:00
Cohee
112e8f224c
Use alternate method of determining URLs, consolidate logs format
2024-03-03 16:45:26 +02:00
Cohee
39c588f30e
Showdown: parse single underscores as italics
2024-03-03 15:26:29 +02:00
RossAscends
1e555bcb8f
markdown support in spoiler display
2024-03-03 19:54:21 +09:00
Bronya-Rand
668d1f0fb9
feat: add `importUUID` API to get Pyg/Janny/Chub bots without link
2024-03-03 03:31:39 +00:00
Wolfsblvt
c0e112d195
Tag Folders: inline info for groups and avatars
...
- Add list of character avatars to folders (overflow hidden)
- Add and/or move count of characters for both groups and folders in overview
- Add name list of all chars for groups, above tags
- Replace alt texts of all avatar images with the entity name
- Made title/mouseover tooltip more useful with separation between types and their names
- refactored CSS usage of avatar sizes to global variables
- grid view alignment changes
2024-03-03 02:12:18 +01:00
Wolfsblvt
1faf8b7ee2
Tag Folders: Sync tag filters and bogus drilldown
...
- When you select or unselect a filter that is also a folder, the folder gets put into the drilldown
- When you click a folder or go back, the tag selection is synced accordingly
- Do not throw away bogus/tag filter on redraw/refresh of the list
2024-03-03 02:12:18 +01:00
Wolfsblvt
3e44dddfda
Tag Folders: Drilldown for select and improved filter
...
- drilldown visible for bogus folder selections
- drilldown can be changed and refreshed
- enhanced filters (remove empty folders/tags from list by default)
2024-03-03 02:12:17 +01:00
Wolfsblvt
25b528ee4f
Tag Folders: add tag folder sorting and enabling
...
- make tags sortable per drag&drop (then sorted everywhere)
- each tag can individually be enabled as folder
- fix redraw of tags/entity list on tag changes
2024-03-03 02:11:35 +01:00
berbant
8769630b68
Character source link processing
2024-03-02 23:37:18 +04:00
Cohee
456c4c333f
Creator notes in char list are no longer first line only.
2024-03-02 19:46:59 +02:00
Cohee
95c49029f7
Add aphrodite model selector
2024-03-01 23:02:43 +02:00
Cohee
d57b5ad6f7
Fix code style
2024-03-01 21:35:33 +02:00
Cohee
81bf6cb399
Merge pull request #1872 from Technologicat/fragment-search-chats
...
Fragment search (a.k.a. swoop) for Manage chat files
2024-03-01 21:30:41 +02:00
Cohee
b716dfbc0d
Merge pull request #1874 from deciare/underline-text-format
...
Support underlined text formatting
2024-03-01 17:49:14 +02:00
Deciare
d554edc023
Support underlined text formatting.
...
- Enable the `underline` option for Showdown.
- Implement option for underlined text colour.
- Update stylesheet.
2024-03-01 00:35:27 -05:00
Juha Jeronen
e3084dda17
Manage chat files: UX: focus the search field when the view opens
2024-02-29 14:22:51 +02:00
Juha Jeronen
f8f6dd1d90
Manage chat files: fragment search a.k.a. swoop
2024-02-29 14:22:35 +02:00
Cohee
3d84ae026d
Fix formatting
2024-02-29 11:50:41 +02:00
berbant
a85a2bbab1
Merge branch 'SillyTavern:staging' into staging
2024-02-28 22:46:43 +04:00
Deciare
2a4b8ac438
Update displayed prompt bias when auto-saving edits.
...
When Auto-save Message Edits is enabled, the prompt bias string
displayed beneath the textarea wasn't being updated.
2024-02-27 05:17:38 -05:00
Deciare
7885f19e86
Perform macro substitution while updating message.
...
This addresses 3 issues:
1. Prompt bias string was not removed from the text of the edited
message.
2. Macro substitition was not performed in the prompt bias string.
3. Macro substitution was not performed in the edited message text.
2024-02-27 05:17:31 -05:00
Cohee
f962ad5c02
Add OpenRouter as a text completion source
2024-02-25 22:47:07 +02:00
berbant
3c620effaf
Update script.js
2024-02-25 21:19:28 +04:00
Cohee
fc289126fa
Add event type for text completion generation request settings ready
2024-02-24 21:45:33 +02:00
Cohee
d5bf9fc28c
Non-streaming logprobs for Aphrodite
2024-02-24 20:53:23 +02:00
Cohee
d140b8d5be
Parse non-streaming tabby logprobs
2024-02-24 20:10:53 +02:00
Cohee
3441667336
#1853 Add WI/Script link by entry automation id
2024-02-24 17:22:51 +02:00
Cohee
13aebc623a
Merge pull request #1854 from deciare/llamacpp-probs
...
Request and display token probabilities from llama.cpp backend
2024-02-24 15:06:28 +02:00
Cohee
eaadfea639
Extend debounce duration of logprobs renderer
2024-02-24 15:03:57 +02:00
Cohee
9287ff18de
Fix for non-streaming
2024-02-24 14:50:06 +02:00
NWilson
f569424f3e
Merge branch 'staging' into InfermaticAI
2024-02-22 08:32:10 -06:00
Cohee
711fd0517f
Merge branch 'staging' into pygimport
2024-02-21 11:26:47 +02:00
Cohee
8e66a14e37
Add hints to doc strings about additional command prompts
2024-02-20 02:29:14 +02:00
Cohee
79ba026486
Merge pull request #1840 from Wolfsblvt/slash-commands-menu-actions-allow-custom-prompts
...
Extend impersonate/continue/regenerate with possible custom prompts (via slash commands and popup menu)
2024-02-20 02:26:41 +02:00
Cohee
061b7c6922
Don't try to execute script commands if the message doesn't start with slash
2024-02-20 02:09:01 +02:00
Wolfsblvt
a5ee46cb2a
Only respect slash command, ignore text field
2024-02-19 22:36:32 +01:00
Wolfsblvt
550d8483cc
Extend impersonate/continue/regenerate with possible custom prompts
...
- Use custom prompt provided via slash command arguments (similar to /sysgen and others)
- Use written text from textbox, if the popout menu actions are clicked
2024-02-19 22:23:58 +01:00
NWilson
030806bf1e
Merge remote-tracking branch 'origin/staging' into InfermaticAI
2024-02-19 10:14:06 -06:00
Cohee
3c2113a6e7
Add ability to preserve file names when loading from assets downloader
2024-02-19 00:17:23 +02:00
Cohee
e4a48cd28f
Add pyg hint to import UI
2024-02-17 03:54:13 +02:00
NWilson
8075e4cd1e
Changes
2024-02-16 09:07:06 -06:00
NWilson
b5887960b6
Merge branch 'release' into InfermaticAI
2024-02-16 08:53:04 -06:00
Cohee
9d713825c2
#1827 Consolidate {{group}} macro behavior
2024-02-12 16:23:01 +02:00
Cohee
72256110a7
Unbreak current chat rename
2024-02-12 02:55:16 +02:00
Cohee
354c52d997
#1814 Fix regex placement attribution
2024-02-11 16:52:14 +02:00
Cohee
03ad72b6c7
Merge pull request #1802 from Technologicat/modelname
...
{{model}} substitution to get name of current LLM
2024-02-08 11:36:02 +02:00
Juha Jeronen
a49d0f1050
use getGeneratingModel
2024-02-08 11:13:54 +02:00
Cohee
04372848c8
Fix for undefined chats
2024-02-07 23:58:05 +02:00
Juha Jeronen
2dcb490e43
add {{model}} substitution macro to get name of current LLM
...
This is useful in the character card for an AI assistant, see #1774 .
Tested with the Textgen backend, but should work with others too.
Horde will show only "Connected", and Novel will show the tier,
but Kobold and Textgen will show the model name.
If not connected, on any backend, will show "no_connection".
2024-02-07 23:29:32 +02:00
Juha Jeronen
c1a5b50aae
improve description for consistency
2024-02-07 23:12:21 +02:00
Juha Jeronen
5183fb40a2
refactor to improve proposed implementation of /getchatname
2024-02-07 23:09:51 +02:00
Juha Jeronen
5d1f3b13ea
add /getchatname slash command to get name of current chat file
...
Example:
/getchatname | /echo {{pipe}}
2024-02-07 22:51:41 +02:00
Cohee
8ecab19966
Merge pull request #1798 from oobabooga/staging
...
Add API key field for text-generation-webui
2024-02-07 19:24:42 +02:00
Juha Jeronen
f0cffb3dd9
fix /delchat for characters with lots of chat files
2024-02-07 15:20:37 +02:00
oobabooga
21fb143718
Add API key
2024-02-06 20:00:16 -08:00
Cohee
2815990589
Force personas sort before returning to caller
2024-02-05 10:58:35 +02:00
Cohee
f12aeeed90
Firefox copium for persona images
2024-02-05 02:18:44 +02:00
Cohee
7ac6ed267f
#1782 OpenAI multiswipe
2024-02-04 03:36:37 +02:00
Cohee
37d94a4331
#1775 Fix personas name sorting
2024-02-03 01:52:57 +02:00
Cohee
303fb09388
Show persona file name on hover
2024-02-02 04:09:12 +02:00
Cohee
a746077a1e
Sort personas by name.
2024-02-02 04:07:51 +02:00
Cohee
33c452df3e
Fix navigation if new persona is on the first page
2024-01-31 11:23:57 +02:00
Cohee
fa73c523f0
Persist current page on persona actions
2024-01-31 11:01:50 +02:00
Cohee
f8032ac649
Default to 5 personas per page
2024-01-31 03:34:51 +02:00
Cohee
c01217ac76
Clean-up styles and handlers
2024-01-30 20:16:48 +02:00
Cohee
4542c66664
#1761 Persona management overhaul
2024-01-30 19:12:56 +02:00
Cohee
da7b435b7c
Merge pull request #1751 from kingbased/proxypreset
...
Reverse proxy presets
2024-01-29 22:09:33 +02:00
Cohee
5f1e290bda
Disallow multiple {{original}} macro substitutions
2024-01-29 00:58:29 +02:00
Cohee
a9464daffa
Merge branch 'staging' into macro-separation
2024-01-29 00:51:06 +02:00
Cohee
ef9cdf64cf
Fix swipe buttons display when using /comment after last AI message
2024-01-29 00:37:51 +02:00
Cohee
8037e31c53
Fix {{original}}
2024-01-28 17:31:19 +02:00
valadaptive
44fb746783
Remove dead if statement
2024-01-27 15:25:44 -05:00
valadaptive
29f509179c
Remove getMessageId
...
As far as I can tell, we don't add/remove anything from chat in between
the calculation of newMessageId and subsequent calls to getMessageId.
We can just use newMessageId everywhere.
2024-01-27 13:50:54 -05:00
valadaptive
e475081116
Fix off-by-one in addOneMessage
2024-01-27 13:48:08 -05:00
valadaptive
7f955a59b9
Remove count_view_mes
2024-01-27 13:24:08 -05:00
valadaptive
4bd7364a8e
Change macro substitution order
2024-01-27 13:22:22 -05:00
valadaptive
71f47588cd
Pass macro variables in to evaluateMacros
...
This doesn't cover *all* the variables yet, just the ones that were
previously passed in as arguments. I'll expand this later to separate
the macro parsing from the execution of the functions themselves.
2024-01-27 13:20:44 -05:00
based
aa976d0de2
implemented proxy preset manager
2024-01-27 06:21:00 +10:00
Cohee
1647e5ae49
Merge pull request #1734 from khanonnie/alternative-tokens
...
Implement Token Probabilities UI panel using logprobs
2024-01-26 03:39:25 +02:00
khanon
60044c18a4
Implement Token Probabilities UI using logprobs
2024-01-25 18:34:46 -06:00
lucy
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
Cohee
6012ee5f89
#1740 Open most recent chat when deleting current chat file
2024-01-25 18:55:38 +02:00
Cohee
4abe87f103
#1742 Add /chat-manager command
2024-01-25 18:19:04 +02:00
Cohee
1ae5a8bd66
#1630 Fix display mode regex depth calc
2024-01-25 02:53:39 +02:00
Cohee
3f3529ef89
#1630 Add min/max depth for prompt/display regex scripts.
2024-01-24 22:48:58 +02:00
Cohee
4985afd816
Extend external media checks
2024-01-24 19:14:40 +02:00
Cohee
9f81ea3c1f
Allow double quotes inside of <tags>
2024-01-24 18:05:11 +02:00
Cohee
4823bcf4ff
Add option to forbid external images
2024-01-24 15:47:54 +02:00
NWilson
f29f934c6b
Progress
2024-01-24 06:59:27 -06:00
Cohee
9b42be2334
Reset message editor before switching active chat
2024-01-23 11:00:33 +02:00
Cohee
958cf6a373
Don't append name2 in non-instruct mode if continuing on first message
2024-01-21 23:20:29 +02:00
Cohee
3cd935c0d2
Fix possible prompt overflow on message examples push-out
2024-01-21 23:13:01 +02:00
Cohee
3cb9413541
#1718 Fix message search opening wrong chats
2024-01-20 20:13:41 +02:00
Cohee
4f55824d7f
QR auto-execute on group member draft
2024-01-18 18:08:38 +02:00
Cohee
b8445eb2cd
Add slash commands for instruct and context
2024-01-18 17:24:07 +02:00
Cohee
f966c398ef
Increase preset command timeouts
2024-01-18 16:36:26 +02:00
maver
e4d5eac6cf
Add world info to generate_before_combine_prompts event data
2024-01-15 17:45:50 +01:00
Cohee
ed77f4763a
#1696 Don't cancel generation on first Escape press if editing a message
2024-01-15 03:45:31 +02:00
Cohee
6086cedf2b
Use XHR to load HTML templates
2024-01-12 22:00:08 +02:00
Cohee
4fe13fab8e
Customizable /gen instruct name
2024-01-12 19:16:42 +02:00
Cohee
4e5f01d785
Merge pull request #1668 from valadaptive/macro-cleanups-1
...
Move substituteParams into its own module
2024-01-12 11:57:21 +02:00
valadaptive
05003ccf78
Remove silly debug logging
2024-01-12 04:38:40 -05:00
valadaptive
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
Cohee
3f6f32edad
Add {{mesExamplesRaw}} macro for story string
2024-01-10 14:11:02 +02:00
Cohee
adf82f2ba8
#1663 Add last prompt line to quiet prompts
2024-01-09 01:14:23 +02:00
Cohee
f7b1b490c7
Larger alternate greetings window
2024-01-06 19:59:48 +02:00
Cohee
5f93c30a96
#1627 Bypass status check and custom model for textgen type
2024-01-05 19:15:07 +02:00
Cohee
c69724e1da
Fix GUI Kobold
2024-01-02 10:28:34 +02:00
Cohee
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
Cohee
f53d937782
Fix mistral undefined name
2024-01-01 18:31:17 +02:00
Cohee
9106696f2f
Render prompt manager when switching APIs
2024-01-01 17:06:10 +02:00
Cohee
908bf7a61d
Merge branch 'staging' into generate-cleanups-3
2024-01-01 16:49:35 +02:00
LenAnderson
8cd75cf03d
add event when world info is updated
2024-01-01 14:34:09 +00:00
Cohee
30732ada32
Lint fix
2024-01-01 16:08:24 +02:00
maver
ee70593a7e
Add world info to generate_before_combine_prompts event data
2023-12-28 17:03:36 +01:00
Cohee
8dd4543e93
Remove macro from user messages when using bias
2023-12-28 11:19:56 +02:00
valadaptive
77b02a8d4b
Extract data.error check
2023-12-26 12:41:35 -05:00
valadaptive
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
valadaptive
3c0207f6cb
Move "continue on send" logic out of Generate()
2023-12-25 03:48:49 -05:00
valadaptive
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
valadaptive
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
valadaptive
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
valadaptive
0d3505c44b
Remove OAI_BEFORE_CHATCOMPLETION
...
Not used in any internal code or extensions I can find.
2023-12-25 03:48:49 -05:00
valadaptive
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
Cohee
a9e074dae1
Don't recreate first message if generation was run at least once
2023-12-24 02:47:00 +02:00
Cohee
db3bf42d63
Fix Firefox number arrows not updating the slider
2023-12-23 16:09:03 +02:00
Cohee
09fd772a20
#1579 Add ooba character yaml import
2023-12-21 21:46:09 +02:00
Cohee
4621834c87
Short formatting path for empty messages
2023-12-21 20:50:30 +02:00
Cohee
a85a6cf606
Allow displaying unreferenced macro in message texts
2023-12-21 20:49:03 +02:00
Cohee
39e0b0f5cb
Remove custom Handlebars helpers for extensions.
2023-12-21 20:33:50 +02:00
valadaptive
8fb26284e2
Clean up Generate(), part 2 ( #1578 )
...
* Move StreamingProcessor constructor to the top
Typical code style is to declare the constructor at the top of the class
definition.
* Remove removePrefix
cleanupMessage does this already.
* Make message_already_generated local
We can pass it into StreamingProcessor so it doesn't have to be a global
variable.
* Consolidate setting isStopped and abort signal
Various places were doing some combination of setting isStopped, calling
abort on the streaming processor's abort controller, and calling
onStopStreaming. Let's consolidate all that functionality into
onStopStreaming/onErrorStreaming.
* More cleanly separate streaming/nonstreaming paths
* Replace promise with async function w/ handlers
By using onSuccess and onError as promise handlers, we can use normal
control flow and don't need to remember to use try/catch blocks or call
onSuccess every time.
* Remove runGenerate
Placing the rest of the code in a separate function doesn't really do
anything for its structure.
* Move StreamingProcessor() into streaming code path
* Fix return from circuit breaker
* Fix non-streaming chat completion request
* Fix Horde generation and quiet unblocking
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
2023-12-21 20:20:28 +02:00
Cohee
b3dfe16706
#1575 Fix clean-up WI depth injections
2023-12-21 16:33:21 +02:00
Cohee
ee75adbd2d
Update persona name if it is bound by user name input
2023-12-21 14:56:32 +02:00
Cohee
cf8d7e7d35
Merge branch 'staging' into custom
2023-12-20 18:37:47 +02:00
Cohee
ebec26154c
Welcome message fixed
2023-12-20 18:37:34 +02:00
Cohee
5734dbd17c
Add custom endpoint type
2023-12-20 18:29:03 +02:00
Cohee
041b9d4b01
Add style sanitizer to message renderer
2023-12-20 17:03:37 +02:00
Cohee
b0a4341571
Merge pull request #1574 from artisticMink/feature/before-combine-event
...
Allow extensions to alter the context order.
2023-12-20 15:46:34 +02:00
maver
f30f75b310
Add GENERATE_BEFORE_COMBINE_PROMPTS event
...
Allows for context to be ordered by extensions
2023-12-19 19:11:36 +01:00
Cohee
67dd52c21b
#1309 Ollama text completion backend
2023-12-19 16:38:11 +02:00
Cohee
edd737e8bd
#371 Add llama.cpp inference server support
2023-12-18 22:38:28 +02:00
Cohee
b0d9f14534
Re-add Together as a text completion source
2023-12-17 23:38:03 +02:00
Cohee
180061337e
Merge branch 'staging' into anachronous/release
2023-12-17 21:35:49 +02:00
LenAnderson
fb25a90532
add GENERATION_STARTED event
2023-12-17 17:45:23 +00:00
anachronos
1e88c8922a
Merge branch 'staging' into release
2023-12-17 10:38:04 +01:00
Fayiron
9f2d32524c
Add TogetherAI as a chat completion source, basic
2023-12-16 14:39:30 +01:00
based
583f786d74
finish mistral frontend integration + apikey status check
2023-12-16 07:15:57 +10:00
Cohee
ef17702f6a
Merge branch 'staging' into bg-load-improvements
2023-12-15 17:02:10 +02:00
Cohee
6c16b94f9d
Merge pull request #1540 from valadaptive/refactor-device-check
...
Refactor mobile device check
2023-12-15 17:01:32 +02:00
valadaptive
0ee19d2ede
Set background client-side
2023-12-15 05:45:21 -05:00
valadaptive
7897206cf8
Add a pre-loading screen cover
...
This matches the loader color and exists to prevent a flash of unstyled
content when the page first loads and JS has not yet run.
2023-12-15 05:34:33 -05:00
valadaptive
fbdfa05f81
Replace usage of getDeviceInfo with isMobile
...
We were using getDeviceInfo to check whether we were on a desktop or a
mobile device. This can be done more simply with isMobile, which means
we can stop exporting getDeviceInfo.
2023-12-14 18:37:54 -05:00
valadaptive
769cc0a78f
Rename settings API endpoints
2023-12-14 16:47:03 -05:00
Cohee
cde9903fcb
Fix Bison models
2023-12-14 22:18:34 +02:00
based
ca87f29771
added streaming for google models
2023-12-14 21:03:41 +10:00
based
be396991de
finish implementing ui changes for google models
2023-12-14 11:53:26 +10:00
based
69e24c9686
change palm naming in UI
2023-12-14 11:14:41 +10:00
Cohee
0cd92f13b4
Merge branch 'staging' into separate-kobold-endpoints
2023-12-14 01:33:36 +02:00
Cohee
b957e3b875
Merge pull request #1518 from valadaptive/separate-ooba-endpoints
...
Move Ooba/textgenerationwebui endpoints into their own module
2023-12-14 01:27:05 +02:00
valadaptive
274605a07c
Rename Kobold-related endpoints
2023-12-12 16:42:12 -05:00
valadaptive
5b3c96df50
Rename /textgenerationwebui endpoint
...
I'd like to migrate over to using "textgen" to mean text-generation APIs
in general, so I've renamed the /textgenerationwebui/* endpoints to
/backends/text-completions/*.
2023-12-12 16:40:14 -05:00
valadaptive
7732865e4c
Another explanatory comment
2023-12-12 16:36:47 -05:00
valadaptive
87cbe361fc
Cache stopping strings rather than skipping them
2023-12-12 16:32:54 -05:00
Cohee
3d7706e6b3
#1524 Skip stop strings clean-up during streaming
2023-12-12 23:09:39 +02:00
Cohee
83f2c1a8ed
#1524 Add FPS limiter to streamed rendering
2023-12-12 22:11:23 +02:00
Cohee
9176f46caf
Add /preset command
2023-12-12 19:14:17 +02:00
Cohee
a9a05b17b9
Merge pull request #1517 from LenAnderson/firstIncludedMessageId
...
Add macro for first included message in context
2023-12-12 01:24:57 +02:00
Cohee
299749a4e7
Add prerequisites for websearch extension
2023-12-12 01:08:47 +02:00
LenAnderson
2bdd3672d4
add macro for first included message in context
2023-12-11 23:06:21 +00:00
Cohee
1b11ddc26a
Add vector storage to WI scanning
2023-12-11 22:47:26 +02:00
Cohee
afe3e824b1
Unblock left swipe on swipeId overflow.
2023-12-11 21:16:09 +02:00
Cohee
e713021737
Merge pull request #1511 from valadaptive/more-kobold-cleanups
...
More Kobold cleanups
2023-12-11 20:59:49 +02:00
Cohee
05ab147209
Fix swipes getting stuck when no Horde models selected
2023-12-11 20:46:34 +02:00
Cohee
7482a75bbd
Merge pull request #1493 from valadaptive/generate-cleanups
...
Clean up Generate(), part 1
2023-12-11 20:21:32 +02:00
Cohee
0302686a96
Return from Generate if calling circuit breaker
2023-12-11 19:07:33 +02:00
Cohee
c48e447c42
Add rows and button text to import window
2023-12-11 16:23:47 +02:00
valadaptive
d33cb0d8d1
Clarify getstatus API
...
Instead of "version" and "koboldVersion", have "koboldUnitedVersion" and
"koboldCppVersion", the latter of which is null if we're not connected
to KoboldCpp.
2023-12-10 20:34:11 -05:00
valadaptive
1fbf4394c8
Separate Kobold Horde status function
2023-12-10 20:16:07 -05:00
valadaptive
3ab1962b84
Improve circuit breaker
...
We now track the loop counter as a parameter of Generate that we
decrement with every recursive call, rather than a global variable,
and it *should* now work with quiet prompt generation.
2023-12-10 18:46:28 -05:00
valadaptive
3d7c901464
Remove looping backoff behavior
2023-12-10 18:35:46 -05:00
valadaptive
315d981804
Reject generation on circuit breaker error
2023-12-10 18:13:34 -05:00
valadaptive
ae9445e500
Reject on data.error
2023-12-10 13:56:31 -05:00
valadaptive
5fd466b53f
Fix generateQuietPrompt
2023-12-10 13:54:39 -05:00
Cohee
420d186823
Add reduced motion toggle
2023-12-10 20:02:25 +02:00
valadaptive
33f969f097
Have Generate() return a promise
...
Generate(), being async, now returns a promise-within-a-promise.
If called with `let p = await Generate(...)`, it'll wait for generation
to *start*. If you then `await p`, you'll wait for generation to
*finish*. This makes it much easier to tell exactly when generation's
done. generateGroupWrapper has been similarly modified.
2023-12-10 12:30:10 -05:00
valadaptive
03884b29ad
Always call resolve in Generate()
...
This lets us get rid of the janky hack in group-chats to tell when a
message is done generating.
2023-12-10 12:26:30 -05:00
Cohee
dbd52a7994
Merge pull request #1482 from valadaptive/sse-stream
...
Refactor server-sent events parsing
2023-12-10 18:32:19 +02:00
Cohee
d5140142fb
Merge branch 'staging' into tokenizers-cleanup
2023-12-10 15:51:15 +02:00
Cohee
e0d0e1dd66
Merge pull request #1502 from valadaptive/status-cleanup
...
Clean up getStatus code
2023-12-10 15:49:37 +02:00
Cohee
6be1c6ff10
Merge pull request #1504 from valadaptive/store-compiled-templates
...
Cache compiled Handlebars templates
2023-12-10 15:32:52 +02:00
Cohee
5f1683f43a
More input padding and stricter sanitation
2023-12-10 15:07:39 +02:00
valadaptive
c48bc8a76e
Cache compiled Handlebars templates
...
Since we already have a template cache, it makes sense to store the
templates in it *after* compiling them, to avoid the overhead of
re-compiling them every time we call renderTemplate.
I've also changed the cache from an object to a Map--it's more
semantically correct, and avoids weird edge cases like a template named
"hasOwnProperty" or some other function that exists as an object
property.
2023-12-09 21:29:36 -05:00
valadaptive
499d158c11
Remove last usage of getAPIServerUrl
...
Now that we're not using this in the tokenizers code, we can remove it.
2023-12-09 20:55:34 -05:00
valadaptive
babb127aee
Move NovelAI status functions over to the rest
...
Have all the get(...)Status and event handler registrations in the same
areas, rather than having the NovelAI ones far away. I want to
eventually move all the API-specific stuff into separate modules, but
this will make things cleaner for the time being.
2023-12-09 18:41:51 -05:00
valadaptive
0ea0399ed1
Separate getStatus into Kobold/textgen versions
...
This adds a bit of duplicate code for the time being, but ultimately
makes the code less confusing because we only need to include the bits
that are relevant to the specific API in each function. We can also
remove API parameters that are useless depending on the endpoint.
2023-12-09 18:39:19 -05:00
Cohee
04c83eae71
Use null coalescing operator
2023-12-09 16:07:55 +02:00
artisticMink
4692450975
Enable getPastCharacterChats to work with specific character ids
2023-12-09 14:36:15 +01:00
artisticMink
ba3966e148
Only refresh character list after all deletions have been processed.
2023-12-09 14:31:18 +01:00
valadaptive
3cfc32c16d
Refactor error handling
...
Remove the StreamingProcessor.hook method and use a try-catch block to
await the generator promise and set the generator, handling errors with
onError if it fails.
2023-12-08 18:40:17 -05:00
Cohee
b0e7b73a32
Fix streaming processor error handler hooks
2023-12-08 02:01:08 +02:00
Cohee
990f958f4f
#1484 Consolidate chat name template
2023-12-07 16:59:53 +02:00
Cohee
2417ae9d87
#1484 Display version on close chat
2023-12-07 16:57:47 +02:00
Cohee
9b7a0f3d35
Hide loader before displaying blocking error message
2023-12-07 12:29:12 +02:00
Cohee
bd1f09c644
Add loader for chat renaming
2023-12-07 12:27:18 +02:00
Cohee
698890ae0f
Fix /delchat slash command
2023-12-07 12:20:33 +02:00
valadaptive
6efe95f4f1
Rename chat API endpoints
2023-12-06 19:58:24 -05:00
Cohee
55d7bd6a87
Return last evaluation of random
2023-12-07 02:45:35 +02:00
Cohee
f575e0d61d
Add {{currentSwipeId}} / {{lastSwipeId}} macros
2023-12-07 02:35:24 +02:00
Cohee
b58f14d1d2
Fix bulk menu not working
2023-12-06 00:55:42 +02:00
Cohee
7f703704c7
Display loader on loading past chats
2023-12-06 00:42:41 +02:00
valadaptive
b689b8bd30
Rename character API endpoints
...
Precursor to moving the character API into its own module
2023-12-04 17:35:06 -05:00
Cohee
ddd16c1469
Merge pull request #1452 from valadaptive/assets-router
...
Use Express router for assets + "files" endpoints
2023-12-04 21:29:52 +02:00
Cohee
1ac494d468
Don't attempt to send files on dry runs.
2023-12-04 21:28:36 +02:00
Cohee
3ad7d5d520
Negotiate formatting with VS Code autoformat
2023-12-04 20:59:11 +02:00
valadaptive
5f1bed1e70
Enable object-curly-spacing lint
2023-12-04 12:32:41 -05:00
valadaptive
3c59b5b7a5
Fix holdover textgenerationwebui_settings
2023-12-03 17:36:25 -05:00
valadaptive
9c33ddbafc
Make textgen settings type checks more concise
2023-12-03 14:56:01 -05:00
valadaptive
047c897ead
Remove is[API] functions
...
Just use an equality comparison. It's a bit longer, but only because
"textgenerationwebui_settings" is a long identifier.
2023-12-03 14:56:01 -05:00
valadaptive
ba54e3dea0
Replaces is_[api] params with api_type param
...
These were 5 mutually-exclusive booleans, which can be replaced with one
param that takes on 5 values, one for each API type.
2023-12-03 14:56:01 -05:00
Cohee
939e938ba2
Disallow multiswipe for quiet gens
2023-12-03 20:56:25 +02:00
Cohee
1786b0d340
#1403 Add Aphrodite multi-swipe
2023-12-03 20:40:09 +02:00
Cohee
676cc7731e
#1436 Add unlock to response length
2023-12-03 18:30:21 +02:00
Cohee
91811f63b5
lint: Fix JSdocs
2023-12-03 14:23:20 +02:00
Cohee
4cb9cd128f
Rename bookmarks to checkpoints
2023-12-03 03:11:14 +02:00
Cohee
2c949b672a
Fix bulk edit and message context action styles
2023-12-03 02:17:02 +02:00
Cohee
c9ab85d8c9
Add /forcesave command
2023-12-03 00:53:45 +02:00
LenAnderson
1eb32b247e
add close stop for cancel button
2023-12-02 21:45:08 +00:00
LenAnderson
c10e298777
fix old popup closing next popup
2023-12-02 21:22:58 +00:00
Cohee
ff46a249d8
Add {{maxPrompt}} macro
2023-12-02 22:47:43 +02:00
Cohee
6e09e45651
Fix /trigger and /continue auto-execution
2023-12-02 22:34:46 +02:00
Cohee
64a3564892
lint: Comma dangle
2023-12-02 22:06:57 +02:00
Cohee
08fedf3a96
lint: Use 4 space indent
2023-12-02 21:56:16 +02:00
Cohee
c63cd87cc0
lint: Require semicolons
2023-12-02 21:11:06 +02:00
Cohee
9faa1e34b0
Merge branch 'staging' into singlequote
2023-12-02 20:43:41 +02:00
Cohee
a28c23d295
Wait for generation unlock before running continue or trigger
2023-12-02 20:12:36 +02:00
valadaptive
a37f874e38
Require single quotes
2023-12-02 13:04:51 -05:00
valadaptive
518bb58d5a
Enable no-unused-vars lint
...
This is the big one. Probably needs thorough review to make sure I
didn't accidentally remove any setInterval or fetch calls.
2023-12-02 12:11:19 -05:00
valadaptive
39bbef376f
Enable no-undef lint
...
I'm not sure where run_edit is supposed to go or if any logic is
missing. I just made my best guess.
2023-12-02 12:11:19 -05:00
valadaptive
66f704bdda
Refactor prompt itemization to not redeclare vars
2023-12-02 12:11:19 -05:00
valadaptive
45ad0683d9
Remove characterName silliness
...
If mes.name is name1, we set it to name1. Otherwise, we set it to
mes.name. It's always mes.name.
2023-12-02 12:10:31 -05:00
valadaptive
b023312117
Enable no-useless-escape lint
2023-12-02 10:32:26 -05:00
valadaptive
0a27275772
Enable no-extra-semi lint
2023-12-02 10:32:26 -05:00
valadaptive
27e63a7a77
Enable no-case-declarations lint
2023-12-02 10:32:26 -05:00
Cohee
6b348f6128
Fix trailing stopping strings removal
2023-12-01 18:55:11 +02:00
Cohee
bb9d302c3a
Don't skip ephemeral stop strings if there are no custom stop strings
2023-12-01 17:18:30 +02:00
RossAscends
59880ee171
disallow newlines in onboarding username
2023-12-01 17:43:05 +09:00
RossAscends
862fc56b39
Merge branch 'staging' of https://github.com/Cohee1207/SillyTavern into staging
2023-12-01 11:39:39 +09:00
RossAscends
c050f2c44d
better manual input for normal sliders
2023-12-01 11:39:37 +09:00
Cohee
bb727d5f9c
Insert files before user text, not after
2023-12-01 03:54:28 +02:00
Cohee
ddd4fac38c
Fix {{mesExamples}} strip behavior with in story string
2023-11-30 19:47:57 +02:00
Cohee
19df1f52cd
Vector storage file retrieval
2023-11-30 00:01:59 +02:00
Cohee
e0bf2b8e3e
[FEATURE_REQUEST] Sending PDF/HTML files? #1414
2023-11-29 17:51:30 +02:00
Cohee
b0d21659eb
/inject command to add prompt injections
2023-11-28 01:44:13 +02:00
Cohee
188897a3df
Add "at" argument to commands sending a message
2023-11-27 19:48:49 +02:00
Cohee
edafb8dd13
Repurpose trigger command not just for groups
2023-11-27 11:16:40 +02:00
dllt98
50ebd1cf66
Add support for importing character from JanitorAI ( #1401 )
...
* Add Janny support
* Add description
* Remove unofficial JanAI mirror
2023-11-27 03:29:19 +02:00
Cohee
f04c277f03
Add optional {{mesExamples}} to story string
2023-11-26 19:47:23 +02:00
Cohee
fb08552d46
Add instruct mode sequence macros
2023-11-26 16:37:05 +02:00
Cohee
c328d6f04a
Add QR auto-exec on app startup
2023-11-26 02:12:31 +02:00
RossAscends
df15a00430
resolve roll&random before parsing macro var commands
2023-11-26 06:27:13 +09:00
Cohee
67fa9c9595
Allow dice rolls in {{random}}
2023-11-25 20:11:47 +02:00
RossAscends
9645034b09
reverse compatibility for old random method
2023-11-26 03:08:03 +09:00