Commit Graph

5970 Commits

Author SHA1 Message Date
1f7c65b45a #3982 CC: Fix visual duplication of presets on renaming 2025-05-24 00:01:50 +03:00
6a67e54ff8 Groups: fix resetting chat metadata on renaming group members 2025-05-23 22:02:59 +03:00
ed2e6fff6e OpenAI: add gpt-image-1 model 2025-05-23 20:33:27 +03:00
58832d1a75 MistralAI: add devstral models 2025-05-23 20:16:56 +03:00
57b81be9ce Caption - allow custom endpoint for xAI 2025-05-22 23:03:04 +03:00
fd0e0945b3 Remove duplicates from group chats list on load 2025-05-22 22:58:26 +03:00
5ac472fbac Implement creator's note style tag preferences (#3979)
* Implement creator's note style tag preferences

* Decouple external media preference from style preference

* Allow explicitly empty prefixes in decodeStyleTags

* Fix Copilot comments

* Refactor global styles management into StylesPreference class

* Refactor openAttachmentManager to return an object instead of an array

* Unify header structure

* Re-render characters panel on setting initial preference

* Add note about classname prefixing

* Rename event handler
2025-05-22 22:32:53 +03:00
62c2c88a79 + captioning and multimodal 2025-05-22 21:17:34 +03:00
edf307aa9c claude 4 2025-05-22 21:14:13 +03:00
ade45b6cd1 Allow prompt post-processing for all sources. Add 'single user msg' processing (#4009)
* Allow prompt post-processing for all sources. Add 'single user msg' PPP type

* Fix copilot comments

* Fix typo in element id

* Remove redundant conditions

* Lint fix

* Add link to PPP docs
2025-05-22 20:36:22 +03:00
157315cd68 Add Vertex AI express mode support (#3977)
* Add Vertex AI express mode support
Split Google AI Studio and Vertex AI

* Add support for Vertex AI, including updating default models and related settings, modifying frontend HTML to include Vertex AI options, and adjusting request processing logic in the backend API.

* Log API name in the console

* Merge sysprompt toggles back

* Use Gemma tokenizers for Vertex and LearnLM

* AI Studio parity updates

* Add link to express mode doc. Also technically it's not a form

* Split title

* Use array includes

* Add support for Google Vertex AI in image captioning feature

* Specify caption API name, add to compression list

---------

Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
2025-05-22 20:10:53 +03:00
6dc59b9fd3 Don't let tag management shrink vertically 2025-05-22 01:04:54 +03:00
d336ea7a13 Add rounded square avatars theme option 2025-05-22 00:39:00 +03:00
ae1017edcb Do not regenerate group greeting messages in tainted chats 2025-05-21 23:10:35 +03:00
94c30837a2 Fix attaching files to permanent assistant from welcome screen 2025-05-21 22:39:49 +03:00
8b6e2a0fe1 Return set toast position on container init 2025-05-21 20:55:11 +03:00
34490c9614 Display loader earlier, init toast classes in power-user 2025-05-21 20:35:03 +03:00
1aa7d1d5a5 meta-theme color matches UI Background 2025-05-21 21:01:28 +09:00
8dff355d5d xtc block filtering, GO 2025-05-21 19:25:14 +09:00
da16c551f0 more toasty edge case fixes 2025-05-21 19:03:26 +09:00
b3e317393b console log cleanup 2025-05-21 16:03:37 +09:00
f145dfcb2d fix edge cases, put toastr on a diet 2025-05-21 15:35:12 +09:00
87f547cd87 add option for toastr location to themes 2025-05-21 15:07:47 +09:00
074ca4a55b flash preview 2025-05-20 21:22:00 +03:00
77f5ef3424 Hide tag for character (#4019)
* Add tagOptions parameter to printTagList for character-specific filtering

* Add toggle functionality to hide tags in tag management popup

* Add translations for "Hide on character card" in multiple locale files

* Add is_hidden_on_character_card property to newTag function

* applied linter

* revert back `DEFAULT_TAGS_LIMIT`

* Remove debug logs

* Adjust HTML

* Render list and save settings on toggle change

* Make tag manager wide

---------

Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
2025-05-20 20:41:03 +03:00
8d7648ccf7 working fix for logprob reroll with autoparsed reasoning (#3998)
* working fix for logprob reroll with autoparsed reasoning

* fix prefix being added all the time

* Code clean-up

---------

Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
2025-05-19 20:30:03 +03:00
e5de348b2e Add missing await in getGroupChat 2025-05-19 10:37:54 +03:00
92e80d3bad hideMutedSprites is hilariously broken 2025-05-19 01:15:40 +03:00
d06789b8dc Check for chat changed before displaying welcome panel 2025-05-19 00:39:19 +03:00
864a733663 "Bind preset to connection" toggle (#3999)
* Implement THE TOGGLE

* Don't force reconnect on preset switch if toggle off

* Don't clear custom models list either
2025-05-17 20:40:58 +03:00
213a619b33 Change server ping to POST method
Closes #4006
2025-05-17 16:50:02 +03:00
9438b5c4aa Cancel debounced metadata save before clearing chat 2025-05-17 15:44:51 +03:00
e52b3afea9 Wait for current chat to finish saving before allowing to switch 2025-05-17 08:45:12 +03:00
f6ab33d835 Reverse CC prompt manager's injection order of "Order" to match World Info (#4004)
* Reverse CC injection "Order" to match World Info

* Set CC injection order default to 100

* Update non-PM injects order + add hint

* Update default order value on inject

---------

Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
2025-05-16 23:53:37 +03:00
e9bc2d8af0 Force close forms on Prompt Manager init 2025-05-16 22:12:45 +03:00
817474c60d Do no automatically apply non-markdown for context separators (#4003) 2025-05-16 19:57:56 +03:00
7a23fe794e Hide buttons on welcome assistant message 2025-05-14 10:41:15 +03:00
587cecb12c Join recent chat/group queries 2025-05-14 10:25:38 +03:00
155172a2b4 Dynamically update show more title 2025-05-14 00:49:33 +03:00
dfbc5ec4ac Fix array slicing, decrease default recent display to 3 2025-05-14 00:42:04 +03:00
cb380863e2 Keep scroll up on welcome display 2025-05-14 00:25:35 +03:00
49c1ee1373 Update avatar title format 2025-05-14 00:21:12 +03:00
9744e6ab2f Button enlargement therapy 2025-05-14 00:15:33 +03:00
21252cf2dd Fix empty chat if creating new assistant 2025-05-13 21:44:24 +03:00
5a799042b1 Optimize fetching recent chats by using Promise.all for concurrent data retrieval 2025-05-13 20:41:26 +03:00
2b93fd37e3 Focus on send textarea on opening temp chat 2025-05-13 20:28:57 +03:00
6a394c0c3e Only render if chat is clear 2025-05-13 19:57:00 +03:00
249cb7777c Merge branch 'staging' into welcome-screen 2025-05-13 19:52:40 +03:00
6e35afa6ec Fix extension prompts injects 2025-05-13 10:04:43 +03:00
b261354280 Add "More" menu hint 2025-05-13 01:35:51 +03:00