7064ce81c7
Exported getChatCompletionModel with optional parameter
2025-02-25 15:45:35 +03:00
b8ebed0f4c
Claude 3.7 think mode
2025-02-24 23:43:13 +02:00
82b74628c6
Sonnet 3.7
2025-02-24 21:06:12 +02:00
10a72b8c80
Merge branch 'staging' of github.com-qvink:SillyTavern/SillyTavern into get_chat_completion_presets_from_preset_manager
2025-02-23 21:24:13 -07:00
7eff895e88
Allowing the presetManager to return presets for chat completion
2025-02-23 21:23:43 -07:00
e7d38d95d0
Add max context size for llama-guard-3-8b model
2025-02-22 14:37:53 +02:00
15769a7643
Add context sizes for new groq models
2025-02-22 14:36:32 +02:00
5c79c8e162
[chore] Reformat new code
2025-02-22 12:47:19 +02:00
13f76c974e
reasoning or reasoning_content
2025-02-22 16:09:42 +08:00
6e5db5c41a
Perplexity: Add new models
2025-02-21 23:03:49 +02:00
5de2f8ea2d
Add o1 to vision-supported models
2025-02-13 02:40:34 +01:00
34db46d84b
Merge branch 'staging' into hidden-reasoning-tracking
2025-02-12 20:00:52 +02:00
d1018a824c
Merge branch 'staging' into hidden-reasoning-tracking
2025-02-11 23:45:13 +02:00
d5bdf1cb90
Add settings.json-backed KV string storage
...
Fixes #3461 , #3443
2025-02-11 20:17:48 +02:00
c3dd3e246e
DeepSeek: Add tool calling for -chat model
2025-02-11 00:04:40 +02:00
703e876f4a
Fix and shorten isHiddenReasoningModel
2025-02-10 06:15:47 +01:00
c886de5deb
Move isHiddenReasoningModel
2025-02-08 18:17:38 +02:00
c8e05a34d6
Add gemini pro to hidden thinking models
2025-02-08 01:48:14 +01:00
d94ac48b65
Add thinking time for hidden reasoning models
...
- Streamline reasoning UI update functionality
- Add helper function to identify hidden reasoning models
- Fix/update reasoning time calculation to actually utilize start gen time
- Fix reasoning UI update on swipe
- add CSS class for hidden reasoning blocks (to make it possible to hide for users)
2025-02-08 00:45:33 +01:00
a2aef5ea4a
Use array.includes
2025-02-07 22:04:21 +02:00
cc401b2c9d
Whelp, seems like o1 main still no streaming
2025-02-07 20:12:10 +01:00
95a31cdd98
Remove logit bias from o1 and o3
...
- They do not be supporting it anymore
2025-02-07 19:51:21 +01:00
d1ec9eb8ab
Enabled streaming for o1 and o3
...
- They do be supporting it now
2025-02-07 19:50:01 +01:00
b074f9fa89
feat: update Gemini models
...
- Add new Gemini models (2025/02/05)
2025-02-06 04:50:54 +08:00
4f63b471d1
Save reasoning effort to preset
2025-02-04 10:28:04 +02:00
3f9af45493
Add reasoning_effort for OpenAI models
2025-02-03 23:29:53 +01:00
055a6527fc
PR fixes
2025-02-02 03:10:32 -05:00
eeaec2697b
Update context lengths and remove guard model
2025-02-01 23:54:14 +00:00
e59114c1c5
Another crack at o3
2025-01-31 23:14:41 +02:00
a83e7318b0
Make "request model reasoning" default true
2025-01-31 22:38:11 +09:00
753a99faf9
Support reasoning for OpenRouter text completion
2025-01-31 21:41:56 +09:00
15a3cfcb8a
Perplexity: Add reasoning model, remove deprecated models
2025-01-29 20:57:38 +02:00
3b8fd6f62f
Merge pull request #3345 from SillyTavern/woo-yeah
...
Better reasoning
2025-01-27 22:09:32 +02:00
abe240397d
Set assistant role to bias in CC
...
#3366
2025-01-27 22:01:44 +02:00
03c98fb55a
OpenRouter: Support reasoning blocks
2025-01-24 00:56:44 +02:00
7f9b139ae0
Merge branch 'staging' into woo-yeah
2025-01-24 00:13:06 +02:00
a503f58d0c
Adding reverse proxy support to DeepSeek chat completion ( #3328 )
...
* added reverse proxy settings to deepseek chat completion
* Update chat-completions.js
* Update chat-completions.js
* Update chat-completions.js
* Update chat-completions.js
* Update chat-completions.js
* Update chat-completions.js
* Unify API key requirement
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com >
2025-01-23 09:02:44 +02:00
afae8d02be
The THONKening
2025-01-23 02:52:52 +02:00
ae29f06e44
Gemini: Fix image inlining for new models
...
#3332
2025-01-22 22:38:13 +02:00
11882827c7
Add new Gemini thinking model and its alias, specify context size and vision support
2025-01-22 18:37:43 +08:00
d7bb92be54
deepseek reasoner
...
Closes #3322
2025-01-20 23:31:40 +02:00
1d5cf8d25c
Work on translation
2025-01-12 00:42:58 +07:00
2b3e44cca3
Clear custom model selection on loading presets
2025-01-08 02:06:29 +02:00
1557dec2bc
Revert "Don't auto-select custom model to the first model in the list"
...
This reverts commit d791b54528
2025-01-08 01:46:31 +02:00
d791b54528
Don't auto-select custom model to the first model in the list
2025-01-07 20:39:35 +02:00
6552038712
Update no validate warning
2025-01-04 14:16:25 +02:00
81cb3430bb
Update openai.js: fix i18n
2025-01-04 15:12:55 +08:00
2ca70090aa
Mistral: Fix endpoint validation on status check
2024-12-29 22:39:26 +02:00
69f8d02c53
Fix continue prefill using Claude prefill for non-Claude sources
2024-12-29 22:34:56 +02:00
cdb31699d4
Expose new post-processing as "Semi-strict"
2024-12-29 21:20:15 +02:00
