pedrohsdb
|
b20ee4152a
|
add 1s delay between cached actions (#4418)
|
2026-01-08 14:35:58 -08:00 |
|
Aaron Perez
|
9645960016
|
[SKV-4350] Add OLLAMA_SUPPORTS_VISION env var, update docs (#4351)
Co-authored-by: Suchintan <suchintan@users.noreply.github.com>
|
2025-12-22 20:20:31 -05:00 |
|
Shuchang Zheng
|
55f366ba93
|
add azure blob storage (#4338)
Signed-off-by: Benji Visser <benji@093b.org>
Co-authored-by: Benji Visser <benji@093b.org>
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
|
2025-12-20 00:16:16 +08:00 |
|
Shuchang Zheng
|
71db86cbf0
|
shu/revert transaction pooler (#4339)
|
2025-12-19 22:49:40 +08:00 |
|
pedrohsdb
|
8b8e93a616
|
Pedro/add gemini 3 flash (#4323)
|
2025-12-17 20:52:29 -08:00 |
|
Shuchang Zheng
|
3d54a288ad
|
test transaction pooler db connection in k8s workers (#4290)
|
2025-12-12 20:02:29 -08:00 |
|
Stanislav Novosad
|
a902fa7a6e
|
Add app.REPLICA_DATABASE (#4289)
|
2025-12-12 17:59:01 -07:00 |
|
Suchintan
|
9add06c9a5
|
GPT 5.2 Support, update models (#4287)
Co-authored-by: Suchintan Singh <suchintan@skyvern.com>
|
2025-12-12 18:22:25 -05:00 |
|
LawyZheng
|
86ec31f556
|
http block support multipart (#4259)
|
2025-12-11 01:03:11 +08:00 |
|
pedrohsdb
|
c939d34603
|
set extract-actions thinking budget to 512, others to 1024 (#4249)
|
2025-12-09 12:57:10 -08:00 |
|
pedrohsdb
|
ff1dcfc0cf
|
set GEMINI_THINKING_BUDGET default to 512 (#4242)
|
2025-12-09 10:00:12 -08:00 |
|
LawyZheng
|
0e8d667959
|
set gemini thinking budget (#4237)
|
2025-12-09 15:37:57 +08:00 |
|
Marc Kelechava
|
5e3211afac
|
honor x-www-form-urlencoded in http block (#4232)
|
2025-12-08 17:34:08 -08:00 |
|
pedrohsdb
|
ffa980f1ff
|
feat: reduce GEMINI_THINKING_BUDGET from 1024 to 500 (#4234)
|
2025-12-08 17:00:21 -08:00 |
|
Shuchang Zheng
|
43e89d2991
|
add support for gpt 5.1 (#4197)
|
2025-12-04 17:08:16 -05:00 |
|
Vikas
|
6dad49eb08
|
feat: add custom credential service (#4129)
Co-authored-by: Stanislav Novosad <stas@skyvern.com>
|
2025-12-02 18:25:04 -07:00 |
|
LawyZheng
|
1fff8a2ac6
|
auto close when page number exceeds (#4101)
|
2025-11-26 14:37:14 +08:00 |
|
Shuchang Zheng
|
2608c02f7a
|
lower default page loading time from 90 seconds to 60 seconds (#4076)
|
2025-11-22 21:07:34 -08:00 |
|
Mohamed Khalil
|
d975ca0913
|
Enhance Windows Compatibility with Event Loop Policy and Path Resolution (#3986)
Co-authored-by: Suchintan <suchintan@users.noreply.github.com>
Co-authored-by: Shuchang Zheng <wintonzheng0325@gmail.com>
Co-authored-by: Stanislav Novosad <stas@skyvern.com>
|
2025-11-19 20:16:16 -07:00 |
|
pedrohsdb
|
f7e68141eb
|
add vertex gemini 3 pro config (#4025)
|
2025-11-18 16:13:51 -08:00 |
|
Stanislav Novosad
|
688224caa8
|
SDK: Disable browser logs (#3958)
|
2025-11-11 09:32:49 -07:00 |
|
pedrohsdb
|
76de33edbd
|
removing laminar (#3858)
|
2025-10-29 21:42:27 -07:00 |
|
Jonathan Dobson
|
e1cff63dae
|
make templating lax again (#3846)
|
2025-10-29 10:19:23 -04:00 |
|
Jonathan Dobson
|
299ceb14f3
|
make templating strictness easy to switch between (#3835)
|
2025-10-28 14:01:49 -04:00 |
|
pedrohsdb
|
5d7d668252
|
point flash and flash lite to stable (#3816)
|
2025-10-24 16:45:58 -07:00 |
|
Jonathan Dobson
|
264b1751d4
|
Backend: implement InteractionBlock (#3810)
|
2025-10-24 16:34:14 -04:00 |
|
greg niemeyer
|
de5a55bd66
|
add claude 4.5 haiku support (#3763)
Co-authored-by: Suchintan <suchintan@users.noreply.github.com>
|
2025-10-20 02:23:22 +00:00 |
|
Shuchang Zheng
|
c186418d41
|
introduce llm key for script gen (#3736)
|
2025-10-16 02:50:16 -07:00 |
|
pedrohsdb
|
dfe8d6fb85
|
Refactor LLM config to payload-based approach and add NORMAL/CUSTOM select-agent handlers (#3723)
|
2025-10-15 12:14:22 -07:00 |
|
greg niemeyer
|
cf9e1c2552
|
chore: env path refactor (#3691)
Co-authored-by: Suchintan <suchintan@users.noreply.github.com>
Co-authored-by: Shuchang Zheng <wintonzheng0325@gmail.com>
|
2025-10-12 17:36:24 +00:00 |
|
Stanislav Novosad
|
32e6aed8ce
|
Migrate credentials to Azure Key Vault (#3681)
|
2025-10-10 10:10:18 -06:00 |
|
Shuchang Zheng
|
ea92ca4c51
|
support openrouter qwen model (#3630)
|
2025-10-06 18:55:52 -07:00 |
|
pedrohsdb
|
bb48db6288
|
Updating Gemini flash pointers in registry and frontend to preview-09-2025 (#3584)
|
2025-10-01 15:41:14 -07:00 |
|
Jonathan Dobson
|
f1cea0a179
|
reduce debug session browser session timeout minutes to 20 (#3563)
|
2025-09-30 14:21:19 -04:00 |
|
Jonathan Dobson
|
3fefdecb8a
|
add gemini flash lite to model selector (#3518)
|
2025-09-24 15:01:38 -04:00 |
|
pedrohsdb
|
2024484ede
|
Add auto-completion flash lite support for Gemini 2.5 Flash Lite testing (#3453)
original PR with approval: https://github.com/Skyvern-AI/skyvern-cloud/pull/6309
|
2025-09-17 17:38:02 -07:00 |
|
pedrohsdb
|
9d8a5b9742
|
Setting for check-user-goal in sequential click for dropdown (flash_lite xp) (#3451)
|
2025-09-17 08:52:04 -07:00 |
|
pedrohsdb
|
9742112449
|
setting up a separate handler for parse input or select, for experiment (#3449)
|
2025-09-16 19:05:18 -07:00 |
|
Shuchang Zheng
|
871c63e079
|
ENABLE_CODE_BLOCK = True by default (#3365)
|
2025-09-04 16:23:08 -07:00 |
|
Shuchang Zheng
|
916e4699d0
|
show input value before the value is interpretated into a real secret (#3364)
|
2025-09-04 16:17:01 -07:00 |
|
Shuchang Zheng
|
c197517df8
|
enable ENABLE_CODE_BLOCK by default and disable it for production/staging (#3363)
|
2025-09-04 14:50:46 -07:00 |
|
LawyZheng
|
e0043d002c
|
refactor gemini reasoning effor (#3292)
|
2025-08-25 23:42:42 +08:00 |
|
Shuchang Zheng
|
0a9b58956f
|
gemini reasoning effort medium by default (#3282)
Co-authored-by: lawyzheng <lawyzheng1106@gmail.com>
|
2025-08-25 08:06:46 +00:00 |
|
Shuchang Zheng
|
d119c0ac92
|
store workflow start block code (#3283)
|
2025-08-23 17:27:17 -07:00 |
|
Shuchang Zheng
|
5055daad00
|
GPT-5 Support + Better Logs (#3277)
|
2025-08-22 13:02:15 -07:00 |
|
LawyZheng
|
44d7c73242
|
extend bitwarden credential to support vaultwarden (#3268)
|
2025-08-22 13:02:12 +08:00 |
|
Shuchang Zheng
|
2392252c66
|
script gen: extract action support (#3238)
|
2025-08-19 21:21:05 -07:00 |
|
Shuchang Zheng
|
7c41de3d70
|
use medium as the default reasoning effort (#3223)
|
2025-08-18 11:01:29 -07:00 |
|
Shuchang Zheng
|
c1b676f85e
|
upgrade litellm to support gpt5 reasoning (#3218)
|
2025-08-17 16:39:37 -07:00 |
|
Shuchang Zheng
|
b342ed74e3
|
add gpt5 model option (#3217)
|
2025-08-17 10:18:27 -07:00 |
|