edbbf056a0
remove zod validation
2025-06-18 17:20:11 -03:00
29323fd7bf
claude4
2025-05-23 00:00:15 +02:00
af162e567a
feat: add Google Search tool support and improve token counting safety
2025-05-20 22:50:55 +02:00
87c6dd90cb
dunno
2025-05-20 12:24:51 +02:00
8344fd2e2a
Workaround for qwen3 think/nonthink auto ST compatibility
2025-05-19 10:54:17 +02:00
cc0ece32d0
Edit mistral-ai.ts
2025-05-07 09:54:40 -08:00
551a13498b
mega basic qwen
2025-05-02 04:06:44 +02:00
780b885aeb
basic cohere
2025-05-02 01:41:20 +02:00
d9645025c9
xai update
2025-04-30 21:26:03 +02:00
c1cb395020
mistral update
2025-04-30 20:03:40 +02:00
6628498d5e
again
2025-04-26 00:37:12 -08:00
afe6ad8ac9
gpt-image fix maybe
2025-04-26 10:29:01 +02:00
a16d66a45b
prelim gpt-image (cant test, no access)
2025-04-25 10:38:23 +02:00
2ffce3eff8
..
2025-04-23 20:14:36 +00:00
8197192223
yea fuck it
2025-04-23 19:49:21 +00:00
7e6857fcf5
last attempt, otherwise fuck thinking for now
2025-04-23 19:39:17 +00:00
719cbc3cfa
tf is this
2025-04-23 19:36:36 +00:00
3beea5dcfc
wtf
2025-04-23 19:22:46 +00:00
9213b7088b
Cohee, when I catch you Cohee
2025-04-23 19:10:13 +00:00
d650038f7e
thinking budget according to ST
2025-04-19 02:24:33 +00:00
14a1203be7
New thinking budget for 2.5 flash
2025-04-17 21:13:36 +00:00
5eb4858c69
o1-pro test
2025-04-17 11:33:58 +00:00
aecc934fad
untested 3.7 sonnet, treating it like another 3.5 sonnet model
2025-02-24 18:38:56 +00:00
a8d36f832e
Check tool_result images for vision
2025-02-12 14:09:22 +00:00
17475447a0
Fix anthropic content schema ( penurin/oai-reverse-proxy!1 )
2025-02-12 13:18:21 +00:00
f1c698388e
[Gemini] Support the new thinking config for 2.0 Flash Thinking
2025-01-22 09:59:11 +00:00
496ec09905
Add v1alpha support (needed for 2.0 flash thinking with the new 'thought' parameter), already used by ST
2025-01-04 19:11:02 +00:00
6ea9235ff8
Actually camelCase is canon for Gemini, oops
2024-12-31 08:23:45 +00:00
372ad85283
Support camelCase Gemini params and validate vision
2024-12-31 10:16:04 +00:00
8f4d00ed26
Init commit, some things:
...
- 'Transfer-Encoding: chunked' for o1 requests to prevent CF's 100 second limit
- Better tool/function call support
- Deepseek support
- Handling system as an array for AWS Claude
- Image support for Gemini
- Better o1 support (reasoning effort, developer role, context size)
2024-12-31 00:00:00 +00:00
ba4532b38d
more fixes for annoying gemini API design that allows arrays or single objects for contents parts
2024-10-09 17:11:53 -05:00
161f5aba3e
handles sillytavern using both camel and snake-cased parameters for gemini api
2024-10-06 11:03:48 -05:00
cfb6353c65
updates google ai safety settings schema
2024-09-25 21:19:17 -05:00
81a3ae1746
maybe fixes missing anthropic version header in some cases
2024-09-19 00:50:17 -05:00
6a908b09cb
adds preliminary openai o1 support and some improvements to openai keychecker
2024-09-12 23:03:33 -05:00
578615fbd2
fixes typo in new Claude system prompt schema
2024-08-30 10:23:57 -05:00
51a9ccceb2
supports alternate claude system prompt format
2024-08-27 23:27:20 -05:00
5000e59a61
fix for google makersuite prompt validation/transformation
2024-08-22 14:19:48 -05:00
5e1fffe07d
adds chatgpt-4o-latest
2024-08-15 11:54:42 -05:00
f7fd5f00f2
fixes
esponse_format schema for mistral la plateforme
2024-08-14 14:41:47 -05:00
b58e7cb830
always applies Mistral prompt fixes on messages input
2024-08-14 10:48:55 -05:00
f531272b00
Refactor AWS service code and add AWS Mistral support ( khanon/oai-reverse-proxy!75 )
2024-08-14 04:40:41 +00:00
2f7315379c
adds gemini/makersuite keychecker, native endpoint, and streaming fixes
2024-08-03 21:53:32 -05:00
994b30dcce
adjusts gemini pro model assignment
2024-06-26 13:37:23 -05:00
ca4321b4cb
adjusts openai schema validation to allow
...
ull stop sequence
2024-06-07 14:29:18 -05:00
34a673a80a
adds option to disable multimodal prompts
2024-03-23 14:30:14 -05:00
59107af3d6
minor fixes for google sheets backend for anthropic-chat
2024-03-17 12:08:11 -05:00
6cf029112e
adds Anthropic's SOTA Haiku model; misc code cleanup
2024-03-13 20:48:05 -05:00
7610369c6d
adds dall-e full history page and metadata downloader
2024-03-10 14:53:11 -05:00
37f17ded60
removes OpenAI max_tokens default as that isn't aligned with the real API
2024-03-10 12:32:15 -05:00
Nopm