Commit Graph

335 Commits

Author SHA1 Message Date
cthomas
c81c0ac8e0 feat: add anthropic token counter for cloud (#2289) 2025-05-20 17:10:50 -07:00
Matthew Zhou
8517ec7230 feat: Asyncify model listing for Gemini (#2284) 2025-05-20 16:00:20 -07:00
Matthew Zhou
edc0717579 feat: Asyncify anthropic model listing (#2283) 2025-05-20 15:59:42 -07:00
Matthew Zhou
87dae5d6e7 feat: Asyncify openai model listing (#2281) 2025-05-20 15:24:00 -07:00
Matthew Zhou
26ae9c4502 feat: Add tavily search builtin tool (#2257) 2025-05-19 16:38:11 -07:00
cthomas
9542dd2fd9 feat: configure retries on anthropic client (#2254) 2025-05-19 16:19:27 -07:00
cthomas
fe592eda72 feat: protect against anthropic nested tool args (#2250) 2025-05-19 16:01:59 -07:00
Andy Li
a78abc610e feat: track llm provider traces and tracking steps in async agent loop (#2219) 2025-05-19 15:50:56 -07:00
Sarah Wooders
e8e1869e1a chore: add gemini + vertex to new agent loop (#2230) 2025-05-17 21:47:42 -07:00
Sarah Wooders
65f8db2efd feat: support together in new agent loop and add tests (#2231) 2025-05-17 19:17:08 -07:00
cthomas
067facbfc7 feat: add informative error for max tokens exceeded (#2223) 2025-05-16 14:02:11 -07:00
Kevin Lin
075b4cb519 fix: patch lmstudio qwen (#2155) 2025-05-13 14:42:00 -07:00
cthomas
bafc47c655 test: add additional new agent messaging tests (#2120) 2025-05-12 15:58:52 -07:00
Kevin Lin
9714a0ace4 fix: use auto function calling for together models (#2097) 2025-05-09 17:46:35 -07:00
Andy Li
a45739444f fix: summarization includes tool call message before truncation (#2084)
Co-authored-by: Sarah Wooders <sarahwooders@gmail.com>
2025-05-09 15:01:12 -07:00
Charles Packer
fce28c73e3 fix: make togetherai nebius xai etc usable via the openaiprovider (#1981)
Co-authored-by: Kevin Lin <klin5061@gmail.com>
Co-authored-by: Kevin Lin <kl2806@columbia.edu>
2025-05-09 10:50:55 -07:00
cthomas
7362ba4a41 fix: missing json import (#2073) 2025-05-08 13:33:39 -07:00
cthomas
d9a03cd484 fix: inner thoughts constant (#2070) 2025-05-07 21:33:34 -07:00
jnjpng
f62a06f04d feat: add endpoint to test connection to llm provider (#2032)
Co-authored-by: Jin Peng <jinjpeng@Jins-MacBook-Pro.local>
2025-05-07 16:26:55 -07:00
cthomas
d1180ab7b9 fix: vertex imports (#2063) 2025-05-07 15:44:44 -07:00
Andy Li
77e7e9555f chore: enable vertex experimental (#2053)
Co-authored-by: Caren Thomas <carenthomas@gmail.com>
2025-05-07 14:52:26 -07:00
cthomas
fa4b647e85 feat: add vertex to new agent loop (#2054) 2025-05-07 14:03:07 -07:00
cthomas
db6982a4bc feat: add provider_category field to distinguish byok (#2038) 2025-05-06 17:31:36 -07:00
jnjpng
1d10b66ae1 fix: skip warning logs for valid event types for anthropic (#2014)
Co-authored-by: Jin Peng <jinjpeng@Jins-MacBook-Pro.local>
2025-05-05 17:07:38 -07:00
Sarah Wooders
a4da3c5192 chore: enable flash and fix vertex integration (#2003) 2025-05-05 13:47:28 -07:00
Charles Packer
326bbc5a04 fix: patch o1 support (#1978) 2025-05-02 14:54:25 -07:00
cthomas
8d2ed07e71 feat: add gemini to byok (#1993) 2025-05-02 14:01:23 -07:00
Andy Li
d1865eaa22 fix: handle malformed function calls in vertex (#1987) 2025-05-02 11:45:41 -07:00
cthomas
c4f603d7b6 feat: always add user id to openai requests (#1969) 2025-04-30 23:23:01 -07:00
cthomas
18db9b9509 feat: byok 2.0 (#1963) 2025-04-30 21:26:50 -07:00
Matthew Zhou
b2627ce22a feat: Add thinking budget for vertex gemini (#1960) 2025-04-30 18:37:42 -07:00
cthomas
4016201087 feat: use new model-proxy in production (#1908) 2025-04-30 15:20:54 -07:00
Sarah Wooders
b6095d76e4 fix: trigger gemini retry with ValueError (#1918) 2025-04-28 18:47:29 -07:00
cthomas
a9cd78cc3b fix: put inner thoughts in kwargs for anthropic (#1911) 2025-04-28 16:37:29 -07:00
cthomas
6609372676 feat: add letta-free endpoint constant (#1907) 2025-04-27 12:57:06 -07:00
Charles Packer
fa34df3e6b fix: patch weird OSS / cloud drift by copying in OSS into cloud (#1904) 2025-04-26 23:21:00 -07:00
cthomas
ce2e8f5c4d feat: add llm config per request (#1866) 2025-04-23 16:37:05 -07:00
cthomas
0a1022b910 fix: pydantic serializer warning datetime -> int (#1701) 2025-04-23 14:53:58 -07:00
Charles Packer
9f12d71916 fix: patch o-series (#1699) 2025-04-23 13:41:34 -07:00
cthomas
e0424dd796 fix: tool_name unreachable bug (#1803) 2025-04-19 16:29:14 -07:00
Kevin Lin
87ff03ea03 fix: llm_config.put_inner_thoughts_in_kwargs = True (#1718) 2025-04-15 14:47:54 -07:00
Matthew Zhou
983f750990 feat: Implement resume step after request in new batch agent loop (#1676) 2025-04-15 13:56:22 -07:00
Charles Packer
90f138c829 fix: patch grok-3 and grok-3-fast (skip reasoners for now) (#1703) 2025-04-14 12:55:20 -07:00
Kevin Lin
29c5ef4881 feat: add reasoning effort in LLMConfig (#1697)
Co-authored-by: cpacker <packercharles@gmail.com>
2025-04-13 17:44:10 -07:00
Sarah Wooders
eb69a24fdd fix: force tool_choice to be auto for claude-3.7-sonnet (#1694) 2025-04-12 16:39:36 -07:00
Sarah Wooders
63395514cb feat: translate system to developer or o-series models (#1692)
Co-authored-by: cpacker <packercharles@gmail.com>
2025-04-11 21:59:48 -07:00
Charles Packer
819e1d2bae fix: patch key error (unclear if we should fatally error here, or jus… (#1690) 2025-04-11 21:24:53 -07:00
Kevin Lin
1453ba47c3 fix: patch o1 and o3-mini (#1657) 2025-04-10 13:50:38 -07:00
Matthew Zhou
dec66f928e feat: Finish step_until_request in new batch agent loop (#1656) 2025-04-10 10:19:06 -07:00
Charles Packer
55b75cb855 fix: patch gemini 2.5 pro (#1643)
Co-authored-by: Sarah Wooders <sarahwooders@gmail.com>
2025-04-09 18:35:53 -07:00