Commit Graph

262 Commits

Author SHA1 Message Date
cthomas
3d62f14bac feat: add gating to provider trace persistence in db (#4223)
* feat: make provider trace fetch result nullable

* feat: add flag for persisting provider trace to db
2025-08-26 15:58:26 -07:00
cthomas
2f8a223c03 feat: add new llm client for deepseek [LET-4056] (#4219)
feat: add new llm client for deepseek
2025-08-26 15:14:09 -07:00
Kevin Lin
1c3781f68d fix: patch anthropic send message tests (#4173)
Co-authored-by: Sarah Wooders <sarahwooders@gmail.com>
2025-08-25 21:17:08 -07:00
Kevin Lin
80ea4a0608 fix: pass thinking to anthropic client (#4150) 2025-08-25 13:36:55 -07:00
jnjpng
feb232f04a fix: mcp schema generation and non-strict schema validation
Co-authored-by: Jin Peng <jinjpeng@Jins-MacBook-Pro.local>
2025-08-22 15:45:33 -07:00
cthomas
be3e562087 feat: add new groq llm client LET-3943 (#3937)
Co-authored-by: Sarah Wooders <sarahwooders@gmail.com>
2025-08-21 13:13:25 -07:00
cthomas
d0ddc5545c feat: add new xai llm client (#3936) 2025-08-20 15:49:09 -07:00
cthomas
02de0effa6 feat: improve error message for vertex response parsing (#4043) 2025-08-20 09:52:20 -07:00
jnjpng
6562868251 fix: include google_ai model endpoint type when setting reasoning tokens for google reasoning models
Co-authored-by: Jin Peng <jinjpeng@Jins-MacBook-Pro.local>
2025-08-19 14:58:35 -07:00
cthomas
a41f08b672 feat: always override thinking budget for anthropic if not min (#4019) 2025-08-19 14:54:11 -07:00
jnjpng
ccdcbb3b01 fix: require function declarations to be present for setting gemini tool config
Co-authored-by: Jin Peng <jinjpeng@Jins-MacBook-Pro.local>
2025-08-19 12:56:31 -07:00
Sarah Wooders
b39f5b864e fix: patch openai byok (#3966) 2025-08-16 13:41:48 -07:00
Kevin Lin
0583eec2f1 feat: GPT-5 support (#3924)
Co-authored-by: Sarah Wooders <sarahwooders@gmail.com>
2025-08-15 19:01:50 -07:00
Charles Packer
d5b62af62d feat: fix anthropic stream buffering issue (was a missing beta header) (#3933) 2025-08-14 22:26:56 -07:00
cthomas
fc0cb25f92 fix: azure client imports (#3916) 2025-08-14 10:36:08 -07:00
cthomas
a45c59de25 chore: delete legacy azure client (#3911) 2025-08-13 16:24:47 -07:00
cthomas
a941b4fe24 chore: delete legacy bedrock client (#3912) 2025-08-13 16:20:48 -07:00
cthomas
591fa49073 chore: fully sunset cohere (#3910) 2025-08-13 16:05:06 -07:00
cthomas
dac2d8bb16 chore: delete legacy anthropic client (#3908) 2025-08-13 15:53:27 -07:00
cthomas
c44a5dc660 chore: clean up legacy bedrock path (#3906) 2025-08-13 15:26:27 -07:00
cthomas
64000792fd chore: clean up legacy anthropic path (#3905) 2025-08-13 15:09:13 -07:00
cthomas
15e20f194d chore: clean up legacy azure path (#3904) 2025-08-13 14:59:15 -07:00
cthomas
9e06cea0ba chore: clean up legacy together path (#3903) 2025-08-13 14:48:24 -07:00
cthomas
90138325a7 feat: update imports for byok check api (#3890) 2025-08-12 16:36:14 -07:00
cthomas
9f7c533765 feat: add azure byok (#3884) 2025-08-12 15:50:00 -07:00
cthomas
1eb692f62a feat: add azure llm client (#3882) 2025-08-12 14:43:03 -07:00
cthomas
6289ca55a2 feat: refactor byok logic in llm clients (#3880) 2025-08-12 14:19:02 -07:00
cthomas
956a4ad011 feat: add together byok support (#3877) 2025-08-12 13:44:01 -07:00
cthomas
227e472282 feat: add new together llm client (#3875) 2025-08-12 13:37:20 -07:00
Matthew Zhou
5772365285 fix: Fix error messages with malformed gemini call (#3865) 2025-08-11 16:59:19 -07:00
cthomas
639641137d feat: consolidate reasoning model checks (#3862) 2025-08-11 16:55:45 -07:00
jnjpng
b62955f0bf fix: gemini 2.5 thinking models fail to call functions if thinking is fully disabled
Co-authored-by: Jin Peng <jinjpeng@Jins-MacBook-Pro.local>
2025-08-08 16:34:32 -07:00
Sarah Wooders
e5497b1d0d chore: merge oss (#3712) 2025-08-07 22:20:26 -07:00
Sarah Wooders
ce44386011 feat: support opus 4.1 and gpt-5 (#3806) 2025-08-07 15:11:57 -07:00
Matthew Zhou
4b788d11de feat: Support streaming and move endpoint for letta-free (#3780) 2025-08-06 15:33:35 -07:00
Sarah Wooders
f5187583d2 feat: move ollama to new agent loop (#3615) 2025-07-31 13:40:26 -07:00
Andy Li
e2d8b35201 chore: remove excessive warning logging 2025-07-30 14:10:41 -07:00
jnjpng
de3c99d7f5 fix: lmstudio support for qwen and llama
Co-authored-by: Jin Peng <jinjpeng@Jins-MacBook-Pro.local>
Co-authored-by: Charles Packer <packercharles@gmail.com>
2025-07-29 15:57:20 -07:00
jnjpng
cf8c59aab9 feat: allow mcp authentication overrides per agent (#3318)
Co-authored-by: Jin Peng <jinjpeng@Jins-MacBook-Pro.local>
2025-07-28 18:20:58 -07:00
Matthew Zhou
84ea52172a feat: Add ability to disable reasoning (#3594) 2025-07-28 15:30:10 -07:00
Andy Li
9ca1664ed8 feat: support for providers 2025-07-22 16:09:50 -07:00
Andy Li
904d9ba5a2 chore: strings lint cleanup (#3374) 2025-07-18 09:20:45 -07:00
Eric Ly
5f3e23fd2a feat: create 'test connection' bedrock api + fix endpoints for test connection (ant, openai, gemini) (#3227)
Co-authored-by: Eric Ly <lyyeric@letta.com>
2025-07-17 11:39:46 -07:00
Charles Packer
72b472896d fix: add frequency penalty for gpt-4o-mini (#3166) 2025-07-06 11:05:31 -07:00
Matthew Zhou
804ec12ee2 feat: Only add suffix on duplication (#3120) 2025-07-01 13:48:38 -07:00
Matthew Zhou
241f653eb6 fix: Fix constraints and also implement bulk attach (#3107) 2025-06-30 14:27:57 -07:00
Charles Packer
d41cfe4d0f fix: patch annoying user warning caused by not having sonnet/opus 4 listed (#3017) 2025-06-24 19:07:25 -07:00
Andy Li
343dbb5359 feat: timeout configuration for LLM clients + vertex (#2972) 2025-06-23 16:55:23 -07:00
Sarah Wooders
041421e75e fix: remove from mcp so that it works with gemini (#2961) 2025-06-21 21:32:18 -07:00
cthomas
fa362c404f feat: add bedrock client (#2913) 2025-06-19 12:07:00 -07:00