124 Commits

Author SHA1 Message Date
zhangkun9038@dingtalk.com
3e94b5bd0c baid appid remove hardcode 2025-02-13 11:05:07 +08:00
545a8419a7 参数化百度 appid 2025-02-13 02:56:36 +08:00
zhangkun9038@dingtalk.com
71ac22a864 add baidu 2025-02-12 23:47:03 +08:00
zhangkun9038@dingtalk.com
ab9127fcbc remove baidu 2025-02-12 22:38:55 +08:00
zhangkun9038@dingtalk.com
58375d45c3 up 2025-02-11 10:32:29 +08:00
zhangkun9038@dingtalk.com
47e23787e5 custome 2025-02-11 01:46:29 +08:00
zhangkun9038@dingtalk.com
56cf5b5bee try add baidu 2025-02-10 11:58:06 +08:00
zhangkun9038@dingtalk.com
07abe12f54 add request log 2025-02-09 22:17:25 +08:00
zhangkun9038@dingtalk.com
be74f25b82 support baidu bce 2025-02-09 21:42:25 +08:00
zhangkun9038@dingtalk.com
3d639b9eaf Reset code state to origin 2025-02-09 21:06:13 +08:00
zhangkun9038@dingtalk.com
a715664408 add baidu bce platform support 2025-02-09 02:02:11 +08:00
zhangkun9038@dingtalk.com
3f61df6373 add baidu bce platform support 2025-02-09 01:47:25 +08:00
yetone
c2b3cd7a32
fix: check gemini api key () 2025-02-07 13:21:45 +08:00
yetone
402c7f9665
fix: copilot tool histories () 2025-02-06 19:19:50 +08:00
yetone
5f6612fb8c
fix: support multiple tool use () 2025-02-06 16:41:28 +08:00
yetone
d1cc23fa54
fix: multiple tool use histories and disable tools () 2025-02-06 02:46:52 +08:00
yetone
e1125fca54
feat: bedrock use tools () 2025-02-06 00:03:49 +08:00
yetone
3aaf7dad77
feat: tools support copilot () 2025-02-05 23:47:52 +08:00
yetone
1437f319d2
feat: tools ()
* feat: tools

* feat: claude use tools

* feat: openai use tools
2025-02-05 22:39:54 +08:00
yetone
ef4b6077ec
feat: supports openrouter reasoning () 2025-02-04 01:38:18 +08:00
ken
43269cc07f
Feat: Add Amazon Bedrock provider () 2025-02-03 22:33:25 +08:00
yetone
cd7390de21
fix: remove unnecessary think tag () 2025-02-03 22:32:41 +08:00
yetone
8536d102be
fix: reasoning content processing () 2025-02-03 21:55:12 +08:00
yetone
5ac934f228
chores: remove debug log () 2025-02-02 02:29:41 +08:00
yetone
b5ac768416
feat: supports reasoning_content () 2025-02-02 02:12:14 +08:00
kernitus
499b7a854b chore: make azure o series models stream 2025-01-29 13:40:43 +08:00
William Heryanto
369410bdb1
fix: Gemini not reaching end state () 2025-01-05 21:11:04 +08:00
hat0uma
0536c6e552
fix(copilot): Prioritize xdg_config for OAuth token references on Windows () 2025-01-05 20:45:25 +08:00
yetone
3ec847e3cb
fix(ci): lua lint () 2025-01-05 17:11:15 +08:00
Larry Lv
ec5d1abf34
fix(openai): support all o series models ()
Before this change, since `max_completion_tokens` was not set for `o` series models, the completion request will time out sometimes. This makes sure it converts the `max_tokens` parameter to `max_completion_tokens` for `o` series models.

I tested this change with `gpt-4o-mini`, `o1-mini` and `o3-mini`, and they all still work as expected.
2025-01-05 13:23:33 +08:00
Sam Jones
9abbec4c5b
fix(copilot): refreshing copilot tokens ()
* fix: wait for github copilot token to refresh before calling completion

* feat: timer to refresh copilot token to prevent 401
2024-12-29 22:58:13 -08:00
kernitus
0d62ffd1cb
fix: azure o1 unsupported options () 2024-12-24 22:40:59 +08:00
yetone
01e05a538b
fix: more reasonable error reporting () 2024-12-18 23:16:41 +08:00
msvechla
6206998f24
chore: allow to pass raw curl args ()
This can be used to pass additional arguments to curl, which can be
helpful when working on new providers like bedrock, that can use curl
arguments for authorization.
2024-12-04 18:57:07 +08:00
Arkuna
57311bf8cd
fix: Get copilot refresh token asynchronously () 2024-12-01 14:00:42 +08:00
Aaron Batilo
e60ccd2db4
feat: enable streaming for o1 models ()
As of a few days ago, o1 models support streaming responses. Please see:
https://community.openai.com/t/openai-o1-streaming-now-available-api-access-for-tiers-1-5/1025430
2024-11-24 17:28:27 +08:00
Shourya Sharma
9d2599df4d
refactor: ♻️ Updated API parsing logic for vertex AI to throw specific error ()
Co-authored-by: Shourya Sharma <shourya.sharma@complyadvantage.com>
2024-11-23 12:47:29 +08:00
yetone
3beed68157
fix: copilot url join () 2024-11-19 06:20:42 +08:00
yetone
e65be50a0a
fix: claude parse response () 2024-11-19 06:03:03 +08:00
yetone
cf2312abbc
fix: provider must be set () 2024-11-19 05:14:04 +08:00
yetone
9891b03656
fix(openai): user and assistant roles should be alternating () 2024-11-17 03:49:02 +08:00
yetone
ff85b9c1e2
refactor: remove redundant local field to facilitate provider configuration () 2024-11-17 02:55:40 +08:00
yetone
4acdcb6e8b
fix: provider inherited_from () 2024-11-17 01:09:33 +08:00
yetone
dfc51b3247
feat: add url_join () 2024-11-17 00:39:03 +08:00
yetone
a3e5053d55
fix: preset vendors missing many fields () 2024-11-16 02:09:14 +08:00
Shourya Sharma
839a8ee25a
feat: Added vertex AI provider for orgs using gemini ()
Co-authored-by: Shourya Sharma <shourya.sharma@complyadvantage.com>
2024-11-15 00:34:58 +08:00
insects
ecaf850859
fix(compat): filter out non value and not user message ()
Co-authored-by: Aaron Pham <Aaronpham0103@gmail.com>
Co-authored-by: Aaron Pham <contact@aarnphm.xyz>
2024-11-07 05:38:56 -05:00
insects
ec9b00db8b
fix(openai): add backward compat for get_user_message ()
Co-authored-by: ming.chen <ming.chen@shopee.com>
Co-authored-by: Aaron Pham <Aaronpham0103@gmail.com>
2024-11-07 02:16:19 -05:00
Christopher Brewin
c516883b99
fix(copilot): refresh token before sending the request ()
Co-authored-by: Aaron Pham <contact@aarnphm.xyz>
2024-11-06 00:07:02 -05:00
yetone
1e8abbf798
feat: memory 🧠 () 2024-11-04 16:20:28 +08:00