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 |
|
Shuchang Zheng
|
ea5620acd2
|
weave LLMCaller.llm_key through to api handler/agent (#2524)
|
2025-05-29 16:49:59 -04:00 |
|
Shuchang Zheng
|
08bf2bc428
|
backend changes extracted from codex/jon/SKY-5016 (#2508)
|
2025-05-29 09:15:04 -04:00 |
|
Shuchang Zheng
|
fc71c32133
|
Add Anthropic Claude 4 and 3.5 Haiku models (#2477)
|
2025-05-26 22:18:20 -04:00 |
|
Shuchang Zheng
|
f49b5c4100
|
add gemini 2.5 flash preview 05-20 (#2434)
|
2025-05-22 14:12:54 -07:00 |
|
Shuchang Zheng
|
3c7ac35d4f
|
use vertex global region (#2326)
|
2025-05-12 10:28:10 +08:00 |
|
Shuchang Zheng
|
1fbaf711b1
|
fix anthropic llm stats (#2313)
|
2025-05-08 14:30:00 -07:00 |
|
Shuchang Zheng
|
349e506dc1
|
shu/remove max completion tokens for ollama (#2300)
|
2025-05-06 12:21:42 -07:00 |
|
Shuchang Zheng
|
e2a82a75d9
|
fix linter errors for config registry & cli (#2292)
|
2025-05-05 00:12:46 -07:00 |
|
Prakash Maheshwaran
|
c3072d7572
|
Added Ollama & Openrouter & Groq & improved cdp browser (#2283)
|
2025-05-05 00:03:23 -07:00 |
|
Shuchang Zheng
|
dbcc48833e
|
fix LiteLLMParams typing (#2285)
|
2025-05-04 01:02:01 -07:00 |
|
Shuchang Zheng
|
8b834436b5
|
anthropic support - dymanic window size / window popup (#2284)
|
2025-05-04 00:40:16 -07:00 |
|
Shuchang Zheng
|
38f8a21d32
|
anthropic CUA - limit image message count (#2265)
|
2025-04-30 18:03:40 -07:00 |
|
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 |
|