Commit Graph

335 Commits

Author SHA1 Message Date
jnjpng
243a2b65e0 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
bde4714294 chore: merge oss (#3712) 2025-08-07 22:20:26 -07:00
Sarah Wooders
b85f8aa43c feat: support opus 4.1 and gpt-5 (#3806) 2025-08-07 15:11:57 -07:00
Matthew Zhou
76c9a58d6f feat: Support streaming and move endpoint for letta-free (#3780) 2025-08-06 15:33:35 -07:00
Sarah Wooders
c2b2d976b6 feat: move ollama to new agent loop (#3615) 2025-07-31 13:40:26 -07:00
Andy Li
c22b9c1af5 chore: remove excessive warning logging 2025-07-30 14:10:41 -07:00
jnjpng
9d8a122da0 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
04511d1ffc 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
d77eb1230f feat: Add ability to disable reasoning (#3594) 2025-07-28 15:30:10 -07:00
Andy Li
58081e3cea feat: support for providers 2025-07-22 16:09:50 -07:00
Andy Li
04e9f43220 chore: strings lint cleanup (#3374) 2025-07-18 09:20:45 -07:00
Eric Ly
396f37156c 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
12c2b49461 fix: add frequency penalty for gpt-4o-mini (#3166) 2025-07-06 11:05:31 -07:00
Matthew Zhou
efca9d8ea0 feat: Only add suffix on duplication (#3120) 2025-07-01 13:48:38 -07:00
Matthew Zhou
5dccccec21 fix: Fix constraints and also implement bulk attach (#3107) 2025-06-30 14:27:57 -07:00
Charles Packer
aa02da3bb3 fix: patch annoying user warning caused by not having sonnet/opus 4 listed (#3017) 2025-06-24 19:07:25 -07:00
Andy Li
734680db81 feat: timeout configuration for LLM clients + vertex (#2972) 2025-06-23 16:55:23 -07:00
Sarah Wooders
630fe0b067 fix: remove from mcp so that it works with gemini (#2961) 2025-06-21 21:32:18 -07:00
cthomas
56493de971 feat: add bedrock client (#2913) 2025-06-19 12:07:00 -07:00
cthomas
eab5a60311 feat: rename aws env vars for bedrock (#2907)
Co-authored-by: Andy Li <55300002+cliandy@users.noreply.github.com>
2025-06-19 10:36:47 -07:00
cthomas
e89164f71b feat: add bedrock to byok (#2891) 2025-06-18 16:03:28 -07:00
Kevin Lin
65530e8380 fix: add exceptions to accept_developer_role (#2848) 2025-06-16 15:14:40 -07:00
Matthew Zhou
4df0268674 fix: Harden string matching for context window exceeded error (#2847) 2025-06-16 14:34:41 -07:00
Kevin Lin
93c15244ab feat: add reasoning models to integration_test_send_message (#2710) 2025-06-13 14:54:37 -07:00
cthomas
c1255dc9d1 feat: make tool calls required for model proxy (#2756) 2025-06-11 11:36:45 -07:00
Matthew Zhou
0399fc8b11 feat: Add prompting to guide tool rule usage (#2742) 2025-06-10 16:21:27 -07:00
cthomas
5ecd8a706c fix: parallel tool calling OpenAI (#2738) 2025-06-10 14:27:01 -07:00
cthomas
b332ebfa85 feat: support multi content part input (#2717) 2025-06-10 13:36:17 -07:00
Matthew Zhou
b53be62e7a fix: Turn parallel tool calling off for OpenAI (#2737) 2025-06-10 13:27:00 -07:00
Matthew Zhou
881506d574 fix: Turn off parallel tool calling for Claude (#2736) 2025-06-10 13:04:20 -07:00
Matthew Zhou
039f5f70d9 feat: Remove debug artifacts (#2734) 2025-06-10 12:26:45 -07:00
cthomas
20e6732f36 feat: add multi-modal input support (#2590) 2025-06-08 18:28:01 -07:00
cthomas
4554f6168b fix: incorrect anthropic tool format hack (#2685) 2025-06-06 15:48:18 -07:00
cthomas
e4da78fce7 fix: gracefully handle too long responses from llm provider (#2677) 2025-06-06 13:13:32 -07:00
Andy Li
d2252f2953 feat: otel metrics and expanded collecting (#2647)
(passed tests in last run)
2025-06-05 17:20:14 -07:00
cthomas
6d094fd196 fix: send message tests (#2656) 2025-06-05 13:57:43 -07:00
Matthew Zhou
470b13f4b9 feat: Add tools for opening and closing files (#2638) 2025-06-04 17:33:18 -07:00
Matthew Zhou
82b3222a52 fix: Make OpenAI context window exceeded error more specific (#2624) 2025-06-04 12:57:51 -07:00
Matthew Zhou
ebccd8176a fix: Add additional testing for anthropic token counting (#2619) 2025-06-03 20:56:39 -07:00
Matthew Zhou
87f4bcad9a feat: Add summarization for more scenarios (#2499) 2025-05-29 11:10:13 -07:00
Sarah Wooders
3354f5fe50 feat: concurrently make embedding request and use async client for OpenAI (#2482)
Co-authored-by: Matthew Zhou <mattzh1314@gmail.com>
2025-05-28 11:35:22 -07:00
cthomas
05e376d521 feat: add property ordering for vertex structured outputs (#2487) 2025-05-28 09:27:26 -07:00
Sarah Wooders
4cc075f1fc feat: add more trace methods (#2471) 2025-05-27 16:56:30 -07:00
cthomas
e813a65351 feat(asyncify): byok in async loop (#2421) 2025-05-25 19:47:20 -07:00
Shangyin Tan
2199d8fdda fix: do not pass temperature to request if model is oai reasoning model (#2189)
Co-authored-by: Charles Packer <packercharles@gmail.com>
2025-05-24 21:34:18 -07:00
cthomas
eaeac54798 fix: google clients thinking config (#2414)
Co-authored-by: Sarah Wooders <sarahwooders@gmail.com>
2025-05-24 09:42:34 -07:00
cthomas
f9d2793caf fix: set thinking budget for vertex tokens (#2367) 2025-05-23 09:07:32 -07:00
cthomas
b554171d41 feat: add tracing to llm clients (#2340) 2025-05-22 13:55:32 -07:00
cthomas
c9aa69d30e fix: google vertex client errors (#2307) 2025-05-21 12:03:50 -07:00
cthomas
095a14cd1d ci: use experimental for send message tests (#2290)
Co-authored-by: Sarah Wooders <sarahwooders@gmail.com>
2025-05-20 18:39:27 -07:00