Shuchang Zheng
|
eacf9d5388
|
resize screenshots to make it compatible with anthropic CUA (#2255)
|
2025-04-30 01:13:36 -07:00 |
|
Shuchang Zheng
|
53f4c23ef9
|
fix bug (#2249)
|
2025-04-30 00:06:59 +08:00 |
|
Shuchang Zheng
|
f4ea546ae4
|
fix anthropic tool result format (#2246)
|
2025-04-29 04:17:50 +08:00 |
|
Shuchang Zheng
|
47ad15a864
|
add vertex ai (#2243)
|
2025-04-29 03:11:56 +08:00 |
|
Shuchang Zheng
|
7e4a193443
|
fix tool_call_input parsing with anthropic sdk (#2242)
|
2025-04-29 02:57:56 +08:00 |
|
Shuchang Zheng
|
1449720038
|
enable thinking in anthropic CUA (#2240)
|
2025-04-29 00:16:22 +08:00 |
|
Shuchang Zheng
|
8e6819c987
|
fix anthropic llm caller routing (#2241)
|
2025-04-29 00:06:37 +08:00 |
|
Shuchang Zheng
|
9e7906a083
|
fix anthropic messages image input pattern (#2239)
|
2025-04-28 23:12:45 +08:00 |
|
Shuchang Zheng
|
1530338cad
|
Anthropic CUA fix (#2238)
|
2025-04-28 18:15:23 +08:00 |
|
Shuchang Zheng
|
a8d237deee
|
use anthropic beta client (#2235)
|
2025-04-28 16:24:12 +08:00 |
|
Shuchang Zheng
|
0a0228b341
|
anthropic CUA (#2231)
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
|
2025-04-28 09:49:44 +08:00 |
|
Shuchang Zheng
|
56cfb55096
|
add LLMCaller that supports message history (#2204)
|
2025-04-24 03:37:26 +08:00 |
|
Shuchang Zheng
|
ef36125b91
|
debug log: Using general model configuration for unknown LLM key (#2223)
|
2025-04-24 02:08:00 +08:00 |
|
Shuchang Zheng
|
fc72240c03
|
bedrock claude 3.7 sonnet (#2203)
|
2025-04-21 15:48:08 +08:00 |
|
Shuchang Zheng
|
7a15ea7405
|
update latest openai model configs for azure & openai (#2202)
|
2025-04-21 14:44:15 +08:00 |
|
Brandon Beiler
|
3d381a60f0
|
Feature: Configuring OpenAI-Compatible (LiteLLM) Models (#2166)
Co-authored-by: bbeiler <bbeiler@ridgelineintl.com>
|
2025-04-21 08:25:59 +08:00 |
|
Suchintan
|
eefddb4105
|
GPT-o4-mini and GPT-o3 support is here (#2170)
|
2025-04-16 21:34:00 -04:00 |
|
Shuchang Zheng
|
3154a9ce10
|
fix llm cost for gpt4.1 (#2172)
|
2025-04-16 15:32:51 -07:00 |
|
Suchintan
|
c829966936
|
GPT-4.1-support (#2159)
|
2025-04-16 02:12:33 -04:00 |
|
Shuchang Zheng
|
7e5e684f53
|
shu/gemini 2.5 pro support (#2109)
|
2025-04-06 00:03:24 -04:00 |
|
Suchintan
|
ff57f9977c
|
Update docs plus init (#2073)
Co-authored-by: Shuchang Zheng <wintonzheng0325@gmail.com>
|
2025-04-03 00:46:57 -04:00 |
|
Shuchang Zheng
|
f924185caf
|
fix cached_tokens & completion_tokens (#1986)
|
2025-03-20 19:56:02 -07:00 |
|
Shuchang Zheng
|
eb3eb4eede
|
track reasoning token and cached token (#1985)
|
2025-03-20 16:42:57 -07:00 |
|
Shuchang Zheng
|
e4a986d286
|
configure logger in the first place in skyvern init (#1965)
|
2025-03-18 11:53:13 -07:00 |
|
Shuchang Zheng
|
205e2b35c0
|
return dummy llm api handler which will raise exception if called (#1954)
|
2025-03-17 12:37:10 -07:00 |
|
Shuchang Zheng
|
8a561c2fbb
|
add SkyvernClient (#1943)
|
2025-03-16 15:46:34 -07:00 |
|
Saurabh Misra
|
21cedc43d1
|
⚡️ Speed up function fix_unescaped_quotes_in_json by 106% (#1891)
Co-authored-by: codeflash-ai[bot] <148906541+codeflash-ai[bot]@users.noreply.github.com>
Co-authored-by: Shuchang Zheng <shu@skyvern.com>
|
2025-03-08 02:34:58 -08:00 |
|
Shuchang Zheng
|
c6a733ff27
|
GPT-4.5 Support (#1868)
|
2025-03-02 23:49:18 -05:00 |
|
Shuchang Zheng
|
d271a84eff
|
Add error message for contextexceedederror (#1866)
|
2025-03-02 23:27:20 -05:00 |
|
Shuchang Zheng
|
179c12db8c
|
add support back for old gpt versions by supporting max_tokens (#1860)
|
2025-03-02 00:16:00 -05:00 |
|
Shuchang Zheng
|
14689b53e4
|
task v2 refactor part 10: ObserverTask -> TaskV2 in backend code (#1839)
|
2025-02-27 23:19:02 -05:00 |
|
Shuchang Zheng
|
31144fa125
|
add anthropic claude3.7 support (#1831)
|
2025-02-24 17:22:17 -08:00 |
|
Shuchang Zheng
|
ffbc95e1b4
|
task v2 refactor part 6 - observer_cruise_id -> task_v2_id (#1817)
|
2025-02-23 16:03:49 -08:00 |
|
Shuchang Zheng
|
713005f403
|
task v2 refactor part 2: observer schema py -> task_v2 schema py (#1814)
|
2025-02-22 03:21:19 -08:00 |
|
Shuchang Zheng
|
22cefee5f9
|
add gemini 2.0 flash (#1745)
|
2025-02-07 14:39:31 +08:00 |
|
Shuchang Zheng
|
4bdc32ce2c
|
add azure o3 mini (#1711)
|
2025-02-04 17:11:29 +08:00 |
|
Shuchang Zheng
|
59756cb1d2
|
O3 Mini support (#1709)
|
2025-02-03 16:07:10 -05:00 |
|
Shuchang Zheng
|
204972e225
|
Add step / task / workflow run / observer metrics as logs (#1698)
Co-authored-by: Suchintan <suchintan@users.noreply.github.com>
|
2025-02-01 14:10:38 -05:00 |
|
Jason
|
c30eba6245
|
feat: add Novita AI deepseek models (#1647)
Co-authored-by: Suchintan <suchintan@users.noreply.github.com>
|
2025-01-27 18:51:09 -05:00 |
|
Shuchang Zheng
|
4578b6fe86
|
add observer thought token count and llm cost (#1595)
|
2025-01-22 07:45:40 +08:00 |
|
Shuchang Zheng
|
c158ad3f21
|
migrate observer to task v2 (#1564)
|
2025-01-15 09:59:18 -08:00 |
|
Jason
|
e54977ef29
|
feat: Add new model provider Novita AI (#1508)
|
2025-01-11 00:08:37 -05:00 |
|
Shuchang Zheng
|
5796de73d1
|
Add AI suggestion endpoints (#1519)
|
2025-01-08 21:45:38 -08:00 |
|
LawyZheng
|
6b4b52a6c4
|
hash long href link (#1500)
|
2025-01-06 23:26:07 +08:00 |
|
Shuchang Zheng
|
175ce55f06
|
recreate index for artifacts table (#1455)
|
2024-12-31 01:38:07 -08:00 |
|
Shuchang Zheng
|
b2fdb187fa
|
Use json_repair (#1453)
|
2024-12-30 14:31:29 -05:00 |
|
Shuchang Zheng
|
5842bfc1fd
|
create cruise related artifact in cruise api (#1355)
|
2024-12-08 21:17:58 -08:00 |
|
Nick Fisher
|
f7f5c47c8e
|
rename GEMINI_FLUSH->GEMINI_FLASH (#1333)
|
2024-12-05 20:28:54 -08:00 |
|
Shuchang Zheng
|
d8c6471c1b
|
amazon nova support (#1315)
|
2024-12-05 00:12:53 -08:00 |
|
Shuchang Zheng
|
6db01f4783
|
gemini 1.5 pro & flash (#1308)
|
2024-12-02 15:59:59 -08:00 |
|