Fimeg/letta-server
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
6,471 Commits 1 Branch 0 Tags
9bff8413a0d526117eb81fd25be0b4ffa50fa333
Commit Graph

50 Commits

Author SHA1 Message Date
Ari Webb
9bff8413a0 fix: fix gemini models reasoning [LET-6228] (#6245) 
* fixed locally

* fix tests

---------

Co-authored-by: Ari Webb <ari@letta.com>
 2025-11-24 19:09:33 -08:00
Ari Webb
7427c0998e feat: gemini parallel tool calling non streaming [LET-5993] (#5889) 
* first hack

* just test non streaming

* stream_steps should pass too

* clean up

---------

Co-authored-by: Ari Webb <ari@letta.com>
 2025-11-13 15:36:39 -08:00
Sarah Wooders
57bb051ea4 feat: add tool return truncation to summarization as a fallback [LET-5970] (#5859) 2025-11-13 15:36:30 -08:00
Kian Jones
6757c7e201 fix: also catch attribute error (.get() on type int for example) (#5650) 
also catch attribute error (.get() on type int for example)
 2025-10-24 15:13:47 -07:00
cthomas
9cb5156ac7 chore: sync 0.12.0 version (#3023) 
Co-authored-by: Matthew Zhou <mattzh1314@gmail.com>
Co-authored-by: Kian Jones <11655409+kianjones9@users.noreply.github.com>
Co-authored-by: Sarah Wooders <sarahwooders@gmail.com>
 2025-10-08 16:10:51 -07:00
cthomas
89321ff29a feat: handle flaky reasoning in v2 tests (#5133) 2025-10-07 17:50:49 -07:00
cthomas
93d9ff01c6 feat: add gemini native thinking (#5124) 
* feat: add gemini native thinking

* update test

* revert comments
 2025-10-07 17:50:49 -07:00
cthomas
6b6b82a07a feat: add streaming support to vertex client (#5106) 2025-10-07 17:50:48 -07:00
Matthew Zhou
df5c997da0 feat: Enable dynamic toggling of tool choice in v3 agent loop for OpenAI [LET-4564] (#5042) 
* Add subsequent flag

* Finish integrating constrained/unconstrained toggling on v3 agent loop

* Update tests to run on v3

* Run lint
 2025-10-07 17:50:47 -07:00
Charles Packer
a4041879a4 feat: add new agent loop (squash rebase of OSS PR) (#4815) 
* feat: squash rebase of OSS PR

* fix: revert changes that weren't on manual rebase

* fix: caught another one

* fix: disable force

* chore: drop print

* fix: just stage-api && just publish-api

* fix: make agent_type consistently an arg in the client

* fix: patch multi-modal support

* chore: put in todo stub

* fix: disable hardcoding for tests

* fix: patch validate agent sync (#4882)

patch validate agent sync

* fix: strip bad merge diff

* fix: revert unrelated diff

* fix: react_v2 naming -> letta_v1 naming

* fix: strip bad merge

---------

Co-authored-by: Kevin Lin <klin5061@gmail.com>
 2025-10-07 17:50:45 -07:00
Kian Jones
b8e9a80d93 merge this (#4759) 
* wait I forgot to comit locally

* cp the entire core directory and then rm the .git subdir
 2025-09-17 15:47:40 -07:00
Kian Jones
22f70ca07c chore: officially migrate to submodule (#4502) 
* remove apps/core and apps/fern

* fix precommit

* add submodule updates in workflows

* submodule

* remove core tests

* update core revision

* Add submodules: true to all GitHub workflows

- Ensure all workflows can access git submodules
- Add submodules support to deployment, test, and CI workflows
- Fix YAML syntax issues in workflow files

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

* remove core-lint

* upgrade core with latest main of oss

---------

Co-authored-by: Claude <noreply@anthropic.com>
 2025-09-09 12:45:53 -07:00
jnjpng
12d8242d94 fix: retry on 500 and 503 for gemini [LET-4185] 
* handle 500 and 503

* timeout

---------

Co-authored-by: Letta Bot <noreply@letta.com>
 2025-09-03 14:02:58 -07:00
jnjpng
c9c9e727b8 fix: retry on MALFORMED_FUNCTION_CALL for gemini [LET-4089] 
---------

Co-authored-by: Letta Bot <noreply@letta.com>
 2025-09-01 07:26:13 -07:00
Charles Packer
5f9210b808 fix(core): update default value [LET-4117] (#4321) 
* fix(core): update default value

* fix: just stage just publish

* fix(core): temporary hardcoding of the anthropic max tokens

* fix(core): patch the gemini
 2025-08-29 16:42:19 -07:00
Kian Jones
fecf6decfb chore: migrate to ruff (#4305) 
* base requirements

* autofix

* Configure ruff for Python linting and formatting

- Set up minimal ruff configuration with basic checks (E, W, F, I)
- Add temporary ignores for common issues during migration
- Configure pre-commit hooks to use ruff with pass_filenames
- This enables gradual migration from black to ruff

* Delete sdj

* autofixed only

* migrate lint action

* more autofixed

* more fixes

* change precommit

* try changing the hook

* try this stuff
 2025-08-29 11:11:19 -07:00
cthomas
5ade6bb236 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
8e49d1a637 feat: improve error message for vertex response parsing (#4043) 2025-08-20 09:52:20 -07:00
jnjpng
0334fabc96 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
jnjpng
fb474c4ac9 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
Matthew Zhou
6c64c8afdd fix: Fix error messages with malformed gemini call (#3865) 2025-08-11 16:59:19 -07:00
cthomas
5cf807574f feat: consolidate reasoning model checks (#3862) 2025-08-11 16:55:45 -07:00
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
Andy Li
c22b9c1af5 chore: remove excessive warning logging 2025-07-30 14:10:41 -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
b332ebfa85 feat: support multi content part input (#2717) 2025-06-10 13:36:17 -07:00
cthomas
20e6732f36 feat: add multi-modal input support (#2590) 2025-06-08 18:28:01 -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
05e376d521 feat: add property ordering for vertex structured outputs (#2487) 2025-05-28 09:27:26 -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
Sarah Wooders
e8e1869e1a chore: add gemini + vertex to new agent loop (#2230) 2025-05-17 21:47:42 -07:00
cthomas
067facbfc7 feat: add informative error for max tokens exceeded (#2223) 2025-05-16 14:02:11 -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
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
Sarah Wooders
a4da3c5192 chore: enable flash and fix vertex integration (#2003) 2025-05-05 13:47:28 -07:00
Andy Li
d1865eaa22 fix: handle malformed function calls in vertex (#1987) 2025-05-02 11:45:41 -07:00
Matthew Zhou
b2627ce22a feat: Add thinking budget for vertex gemini (#1960) 2025-04-30 18:37:42 -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
55b75cb855 fix: patch gemini 2.5 pro (#1643) 
Co-authored-by: Sarah Wooders <sarahwooders@gmail.com>
 2025-04-09 18:35:53 -07:00
Matthew Zhou
f109259b0b chore: Inject LLM config directly to batch api request func (#1652) 2025-04-09 15:56:54 -07:00
Matthew Zhou
3797b0d536 feat: Simplify arguments for LLM clients (#1536) 2025-04-02 14:26:27 -07:00
cthomas
2a36af8a5d feat: add new llm client framework and migrate google apis (#1209) 2025-03-07 16:34:06 -08:00