Fimeg/letta-server
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity
3,426 Commits 1 Branch 0 Tags
ae7d08b2f594483f0694dea136bb69ed4ff78e52
Commit Graph

44 Commits

Author SHA1 Message Date
Charles Packer
56452ae426 fix(core): init attempt at patching the extended thinking bug (#4331) 
* fix(core): init attempt at patching the extended thinking bug

* fix: refactor, fix in a different way be merging instead of dropping, seems to be working

* chore: cleanup

* fix: patch the test - with the new native thinking behavior, anthropic native reasoning does not trigger properly post tool-call

* fix: another attempt

* fix: tests passing locally

* fix: another patch to tests

* fix: pathc more tests

* fix: try turning on the interleave-thinking beta header

* fix: patch test

* fix: add new tests to be more robust

* fix: patch the prompt, now it works more reliably

* fix: typo
 2025-09-01 11:09:02 -07:00
cthomas
8b617c9e0d fix: gemini flash integration test [LET-4060] (#4242) 
* fix: gemini flash integration test

* also update google flash

* catch error in test

* revert test changes

* do try catch again

* remove try catch from streaming tests

* add try catch for summarize test also
 2025-08-27 11:59:15 -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
639641137d feat: consolidate reasoning model checks (#3862) 2025-08-11 16:55:45 -07:00
jnjpng
9d72955e7f fix: lmstudio tests and integration 
Co-authored-by: Jin Peng <jinjpeng@Jins-MacBook-Pro.local>
 2025-08-07 20:02:56 -07:00
jnjpng
fcaa6c78a8 fix: fix and update vllm tests 
Co-authored-by: Jin Peng <jinjpeng@Jins-MacBook-Pro.local>
Co-authored-by: Kian Jones <kian@letta.com>
 2025-08-06 14:37:55 -07:00
Eric Ly
2927295ee7 feat: add formatting for token sizing (#3631) 
Co-authored-by: Eric Ly <lyyeric@letta.com>
 2025-08-04 13:54:44 -07:00
Kian Jones
dfe068b0ce feat(ci): Add LMStudio to self-hosted provider checks (#3623) 
Co-authored-by: Kian Jones <kian@Kians-MacBook-Pro.local>
 2025-08-04 10:38:23 -07:00
Sarah Wooders
f5187583d2 feat: move ollama to new agent loop (#3615) 2025-07-31 13:40:26 -07:00
jnjpng
7f12230c21 fix: manually count tokens for streaming lmstudio models 
Co-authored-by: Jin Peng <jinjpeng@Jins-MacBook-Pro.local>
Co-authored-by: Charles Packer <packercharles@gmail.com>
 2025-07-29 18:12:42 -07:00
Sarah Wooders
6c08adf97e test: run tests with gemini 2.5 instead (#3548) 
Co-authored-by: Kian Jones <11655409+kianjones9@users.noreply.github.com>
Co-authored-by: Kian Jones <kian@letta.com>
Co-authored-by: Matt Zhou <mattzh1314@gmail.com>
 2025-07-29 14:50:28 -07:00
Matthew Zhou
84ea52172a feat: Add ability to disable reasoning (#3594) 2025-07-28 15:30:10 -07:00
Kian Jones
cef4eb1910 feat(ci): Add coverage for self-hosted providers (#2976) 2025-07-21 18:26:23 -07:00
Charles Packer
d81382b9fe refactor: revert the default summarizer to the old style (#3168) 2025-07-06 20:15:22 -07:00
Andy Li
3654fa8c26 feat: expand summarizer providers 2025-07-01 15:07:38 -07:00
Matthew Zhou
54562d88d7 feat: Add required before exit tool rule (#2977) 2025-06-23 17:02:40 -07:00
cthomas
fa362c404f feat: add bedrock client (#2913) 2025-06-19 12:07:00 -07:00
Matthew Zhou
c999875ae9 feat: Add claude 4 config and add more models to CI (#2747) 
Co-authored-by: Charles Packer <packercharles@gmail.com>
 2025-06-18 17:23:52 -07:00
Kevin Lin
a8895ad017 feat: add reasoning models to integration_test_send_message (#2710) 2025-06-13 14:54:37 -07:00
Kevin Lin
ed4b28f3e4 feat: Add files into agent context window on file upload (#1852) 
Co-authored-by: Caren Thomas <carenthomas@gmail.com>
Co-authored-by: Matt Zhou <mattzh1314@gmail.com>
 2025-05-29 18:19:23 -07:00
Sarah Wooders
ed2ddad6a5 chore: add gemini + vertex to new agent loop (#2230) 2025-05-17 21:47:42 -07:00
Sarah Wooders
f076964bd1 feat: support together in new agent loop and add tests (#2231) 2025-05-17 19:17:08 -07:00
cthomas
f67ad6e0c6 test: add agent loop tests (#2088) 2025-05-09 14:20:09 -07:00
cthomas
5187e79a43 feat: use new model-proxy in production (#1908) 2025-04-30 15:20:54 -07:00
cthomas
dc1ecdc902 fix: put inner thoughts in kwargs for anthropic (#1911) 2025-04-28 16:37:29 -07:00
Matthew Zhou
4ba1a29733 feat: Add more models for send_message tests (#1847) 2025-04-22 17:03:21 -07:00
Charles Packer
672845a5dc fix: patch misc broken CI tests (#1645) 2025-04-09 14:50:45 -07:00
Charles Packer
1687d9edb7 feat: add xAI / Grok support (#1122) 
Co-authored-by: Shubham Naik <shub@letta.com>
 2025-02-26 11:02:42 -08:00
Kevin Lin
98f0062416 feat: support deepseek models (#821) 
Co-authored-by: Charles Packer <packercharles@gmail.com>
Co-authored-by: Sarah Wooders <sarahwooders@gmail.com>
Co-authored-by: Shubham Naik <shub@memgpt.ai>
Co-authored-by: Shubham Naik <shub@letta.com>
 2025-02-18 15:28:01 -08:00
Matthew Zhou
52802ca8ee feat: Improve composio error handling (#979) 2025-02-13 17:02:16 -08:00
Sarah Wooders
42ac85efa8 feat: google vertex integration (#980) 2025-02-12 18:06:26 -08:00
Matthew Zhou
96bdb8df1c chore: Add large scale many-messages test (#959) 2025-02-11 10:11:41 -08:00
mlong93
02cca70d78 feat: add support for AWS Bedrock (Anthropic) (#689) 
Co-authored-by: Mindy Long <mindy@letta.com>
 2025-01-17 11:42:21 -08:00
Charles Packer
1272ba6612 fix: changed all instances of 16384 to 8192 (gpt4 context window) (#605) 2025-01-13 14:12:31 -08:00
mlong93
91995ae6ff feat: Adding init tool rule for Anthropic endpoint (#2262) 
Co-authored-by: Mindy Long <mindy@letta.com>
 2024-12-17 15:21:10 -08:00
Charles Packer
f57dc28552 feat: support togetherAI via /completions (#2045) 2024-11-18 15:15:05 -08:00
Matthew Zhou
2d26365e42 fix: Fix summarizer for Anthropic and add integration tests (#2046) 2024-11-15 16:46:12 -08:00
Matthew Zhou
7bb0f53c23 feat: Implement tool calling rules for agents (#1954) 2024-10-30 16:53:41 -07:00
Sarah Wooders
0bd45ab27d fix: update ollama model for testing (#1941) 2024-10-25 15:42:44 -07:00
Matthew Zhou
c18eb466f8 feat: Add put_inner_thoughts_in_kwargs as a config setting for the LLM (#1902) 
Co-authored-by: Matt Zhou <mattzhou@Matts-MacBook-Pro.local>
 2024-10-17 15:54:03 -07:00
Matthew Zhou
b83f77af22 fix: refactor Google AI Provider / helper functions and add endpoint test (#1850) 
Co-authored-by: Matt Zhou <mattzhou@Matts-MacBook-Pro.local>
 2024-10-08 16:55:11 -07:00
Matthew Zhou
446b8f2154 feat: Add listing llm models and embedding models for Azure endpoint (#1846) 
Co-authored-by: Matt Zhou <mattzhou@Matts-MacBook-Pro.local>
 2024-10-08 15:14:55 -07:00
Matthew Zhou
cffd493f75 test: add complex testing for Groq Llama 3.1 70b (#1845) 
Co-authored-by: Matt Zhou <mattzhou@Matts-MacBook-Pro.local>
 2024-10-08 14:22:13 -07:00
Matthew Zhou
1104438490 fix: Fix Azure provider and add complex e2e testing (#1842) 
Co-authored-by: Matt Zhou <mattzhou@Matts-MacBook-Pro.local>
 2024-10-07 17:59:06 -07:00