Commit Graph

161 Commits

Author SHA1 Message Date
pedrohsdb
bc6d7affd5 use explicit vertex credentials for cache manager (#4039) 2025-11-19 17:05:49 -08:00
LawyZheng
0b47dff89d fix cua engine (#4036) 2025-11-20 02:24:00 +08:00
pedrohsdb
f7e68141eb add vertex gemini 3 pro config (#4025) 2025-11-18 16:13:51 -08:00
pedrohsdb
d1c7c675cf cleaned up fallback router (#4010) 2025-11-17 12:08:19 -08:00
pedrohsdb
b7e28b075c parallelize goal check within task (#3997) 2025-11-13 17:18:32 -08:00
pedrohsdb
d88ca1ca27 Pedro/vertex cache minimal fix (#3981) 2025-11-12 10:40:52 -08:00
Marc Kelechava
ab162397cd Support Google Cloud Workload Identity for vertex models (#3956) 2025-11-10 15:56:57 -08:00
pedrohsdb
44528cbd38 Pedro/fix explicit caching vertex api (#3933) 2025-11-06 14:47:58 -08:00
pedrohsdb
0e0ae81693 Improve LLM error message when LLM is down (#3874) 2025-10-31 11:41:07 -07:00
pedrohsdb
46ee020b5d making gpt5 models have temp 1 (#3849) 2025-10-29 09:11:08 -07:00
pedrohsdb
5d7d668252 point flash and flash lite to stable (#3816) 2025-10-24 16:45:58 -07:00
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
pedrohsdb
bcb3414561 magnifex qwen3 featherless implementation (#3764) 2025-10-18 10:44:28 -07:00
Shuchang Zheng
770ddadc2f fix drop_params bug (#3756) 2025-10-17 12:00:34 -07:00
greg niemeyer
9b2bbda3c8 add support for claude sonnet 4.5 (#3692) 2025-10-12 12:57:52 -04:00
greg niemeyer
cb35d966ac fix claude output tokens (#3695) 2025-10-12 11:30:46 -04:00
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
2196d46a47 Revert "Add endpoint for browser sessions history" (#3538) 2025-09-26 16:14:52 -04:00
Jonathan Dobson
1f585a184b Add endpoint for browser sessions history (#3537) 2025-09-26 16:07:27 -04:00
pedrohsdb
f40a2392c8 adding new gemini flash preview models (#3536) 2025-09-26 11:45:22 -07:00
pedrohsdb
dd9d4fb3a9 Pedro/prompt caching (#3531) 2025-09-25 15:04:54 -07:00
pedrohsdb
485b1e025e Pedro/thinking budget optimization (#3502) 2025-09-23 13:44:15 -07:00
LawyZheng
66b2004b70 Use gemini 2_5 flash lite for create_extract_action (#3429) 2025-09-13 16:22:57 +08:00
Shuchang Zheng
0e2aecc75d llm log (#3414) 2025-09-11 18:10:05 -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
b9470ffb44 fix cannot access local variable 'prompt_tokens' where it is not associated with a value (#3286) 2025-08-24 14:25:35 -07:00
Shuchang Zheng
5055daad00 GPT-5 Support + Better Logs (#3277) 2025-08-22 13:02:15 -07:00
Shuchang Zheng
c1b676f85e upgrade litellm to support gpt5 reasoning (#3218) 2025-08-17 16:39:37 -07:00
Shuchang Zheng
e356d9fea0 add support for gpt5 and azure gpt5 series (#3136) 2025-08-07 15:12:47 -07:00
Shuchang Zheng
ffce05c6ef Temperature fix for O-models (#3048) 2025-07-28 14:31:10 -07:00
LawyZheng
95ab8295ce laminar integration (#2887) 2025-07-07 14:43:10 +08:00
Prakash Maheshwaran
d23944bca7 fixed the openrouter stuff (#2630) 2025-07-01 14:02:22 -04:00
Shuchang Zheng
eb0e8a21ee add gemini 2 5 support (#2850) 2025-07-01 13:38:17 +08:00
Asher Foa
a6bf217559 Fix typos (#2807) 2025-06-28 01:26:21 +00:00
Shuchang Zheng
5f26a02dea skip llm artifact creation when empty prompt (#2742) 2025-06-18 14:44:10 +00:00
Wyatt Marshall
346b36fa4d ui tars integration fix (#2714) 2025-06-13 16:52:14 -04:00
LawyZheng
296d2f903b support volcengine + migrate ui tars to volcengine (#2705) 2025-06-13 21:17:32 +08:00
Wyatt Marshall
15d46aab82 ui-tars integration (#2656) 2025-06-13 13:23:39 +08:00
Asher Foa
b0724d2781 vendor and update commentjson since it is abandoned (#2689) 2025-06-12 10:50:16 -04:00
Asher Foa
41332c6976 Add tests (mostly AI generaed/vibe coding) for parse_api_response + existing tests (#2688) 2025-06-11 14:47:58 -07:00
Asher Foa
d2426b8394 Make all llm response parsing/fixing helpers private (#2687) 2025-06-11 21:10:37 +00:00
Shuchang Zheng
9a29d966ab overhual llm key override (#2677) 2025-06-11 23:23:44 +08:00
Shuchang Zheng
09ca00e948 fix timeout for svg and css LLM call (#2662)
Co-authored-by: lawyzheng <lawyzheng1106@gmail.com>
2025-06-10 07:23:15 +00:00
Shuchang Zheng
06d026a231 fallback gemini to gpt + use latest gemini flash 2.5 release (#2588) 2025-06-04 14:41:38 +08:00
Shuchang Zheng
2ddcb9eb0b log duration and prompt_name in llm failure log (#2578) 2025-06-03 10:24:47 -07:00
Shuchang Zheng
aef945cb63 fix llm key override in llm_api_handler_with_router_and_fallback (#2562) 2025-05-31 23:23:37 -07:00
Tiger Shen
73e366bbad Fix Claude 4 model names to use specific versions instead of -latest suffix (#2531) 2025-05-30 18:13:05 -07:00
Shuchang Zheng
5580548e7d support anthropic claude 4 bedrock (#2539) 2025-05-30 16:16:07 -07:00