Fimeg/letta-server
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
6,949 Commits 1 Branch 0 Tags
a92e868ee651c76fb8d93f4bb102aa40094de31b
Commit Graph

110 Commits

Author SHA1 Message Date
Ari Webb
2233d141b1 feat: add codex 5.2 context window (#8704) 2026-01-19 15:54:39 -08:00
Ari Webb
6d859174c2 feat: make conversations throw http busy to stop race condition [LET-6842] (#8411) 
* feat: make conversations throw http busy to stop race condition

* use redis lock instead

* move acquire lock into redis client, integration tests, move lock release into run manager

* fix tests, bug

* conditional import

* remove else

* better release

* run ci

* final reordering lock

* update tests

* wrong naming of lock holder token
 2026-01-12 10:57:49 -08:00
Ari Webb
02f3e3f3b9 fix: fix providers and models persistence (#8302) 2026-01-12 10:57:48 -08:00
Ari Webb
e47eb23522 fix: max output tokens for gemini 3 models (#7322) 2025-12-17 17:31:03 -08:00
Kevin Lin
857139f907 feat: Set reasonable defaults for max output tokens [LET-6483] (#7084) 2025-12-17 17:31:02 -08:00
Ari Webb
4d90f37f50 feat: add gpt-5.2 support (#6698) 2025-12-15 12:02:34 -08:00
Kevin Lin
1ca9df0626 feat: Add memory_apply_patch to base tools (#6491) 
add memory apply patch
 2025-12-15 12:02:34 -08:00
Charles Packer
d3f4d00113 feat(core): add support for gpt-5.1-codex-max (#6528) 2025-12-15 12:02:33 -08:00
Sarah Wooders
86023db9b1 feat: get rid of client injection in args and just make it always available (#6459) 2025-12-15 12:02:19 -08:00
Sarah Wooders
f417e53638 fix: fix cancellation issues without making too many changes to message_ids persistence (#6442) 2025-12-15 12:02:19 -08:00
Sarah Wooders
ceadacd30e feat: support programmatic tool execution (cloud only) (#6441) 2025-12-15 12:02:19 -08:00
Charles Packer
efb5a87313 fix(core): remove threshold multiplier on summ trigger which is bug prone (#6447) 2025-12-15 12:02:19 -08:00
Sarah Wooders
0a0cf391fc fix: fix client injection code (#6421) 2025-12-15 12:02:18 -08:00
Ari Webb
7380eaec13 feat: enable gpt5.1 models [LET-6178] (#6175) 
* hack at gpt51

* revert package lock

* first hack

* default context window

---------

Co-authored-by: Ari Webb <ari@letta.com>
 2025-11-24 19:09:33 -08:00
jnjpng
099da97e7b fix: remove modal image creation logging and fix base imports (#6197) 
base

Co-authored-by: Letta Bot <noreply@letta.com>
 2025-11-24 19:09:32 -08:00
Sarah Wooders
5730f69ecf feat: modal tool execution - NO FEATURE FLAGS USES MODAL [LET-4357] (#5120) 
* initial commit

* add delay to deploy

* fix tests

* add tests

* passing tests

* cleanup

* and use modal

* working on modal

* gate on tool metadata

* agent state

* cleanup

---------

Co-authored-by: Letta Bot <noreply@letta.com>
 2025-11-13 15:36:56 -08:00
Ari Webb
da11d80bf4 fix: add default model gpt4.1 (#5897) 
add default model gpt4.1

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
Charles Packer
60ed435727 fix(core): patch summarizer on letta_agent_v3.py (letta_agent_v1 loop) (#5863) 
* fix(core): patch summarizer

* fix: misc fixes

* refactor: remove fallbacks, instead throw a warning

* refactor: pull out magic number to constant
 2025-11-13 15:36:20 -08:00
Kian Jones
c4c9d12f42 fix: hotfix hardcode context windows to prevent gemini model listing rate limiting (#5731) 
hotfix lol
 2025-10-24 15:14:31 -07:00
Kevin Lin
35b5383724 feat: match line number rendering to Anthropic / OAI defaults (#5492) 2025-10-24 15:13:15 -07:00
Matthew Zhou
de7011e4de feat: Mark certain internal tools as safe to execute concurrently [LET-5614] (#5553) 
* Change execution pattern depending on

* Increase efficiency

* Mark certain tools as parallel safe
 2025-10-24 15:12:26 -07:00
Kian Jones
4bbd760204 feat: add validation to fastapi routes for agent IDs (#5454) 
* change my PR to match Caren's

* add path parameter validation for agent id first

* remove old import

* remove old agent_id_pattern pattern

* add example and fix max/min calculation to include hyphen

* fix regex string interpolation

* example deprecated in favour of examples

* openapi autogen

* change template test to expect 422

* fix 422 swallow

* expect 422 or 400

* rewrite  error codes

* fix hallucinated uuid

* tweaked error message test

* print docker logs on failure
 2025-10-24 15:12:11 -07:00
Charles Packer
d45d29a03f feat: add gpt-5-codex support (#5194) 
* feat(core): add gpt-5-codex

* feat(web): add support to the web hardcoding
 2025-10-07 17:50:49 -07:00
Sarah Wooders
e07a589796 chore: rm composio (#5151) 2025-10-07 17:50:49 -07:00
Sarah Wooders
6016ac0f33 chore: undo fetch_webpage rename (#5132) 2025-10-07 17:50:49 -07:00
Charles Packer
09b173668a feat(core): rename fetch_webpage to web_fetch (#5110) 2025-10-07 17:50:48 -07:00
Kevin Lin
09d9c3ffd4 feat: anthropic tools for claude sonnet 4.5 (#4988) 
* add anthropic memory tools

* memory view working

* update memory examples

* tools

* feat: some changes (#5003)

* feat: added the ability to modify and add descriptions on creation

* fix: kill dead code & write into core_tool_executor instead

* fix: use block_manager not agent_manager where possible, also turn the return string errors into raising exceptions

* fix: cleanup, get rid of more return string errors replaced with valueerror, also drop deadcode

---------

Co-authored-by: Charles Packer <packercharles@gmail.com>
 2025-10-07 17:50:47 -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
Charles Packer
388dd46ffc feat: various performance patches for gpt-5 [LET-4157] (#4381) 
* feat: increase the verbosity of the heartbeat kwarg

* chore: strip docstrings out from the file in which they are not parsed (duplicates inside base.py

* feat: add examples to the docstrings for memory_replace and memory_insert

* feat: add more examples
 2025-09-06 11:23:13 -07:00
Charles Packer
dd1a9a0b7c fix: reduce the default tool return to something more sane [LET-4180] (#4383) 
fix: reduce the default tool return to something more sane (prev limit was allowing like 200k tokens to come through and crash gpt-5
 2025-09-03 13:51:33 -07:00
Matthew Zhou
129dd97902 feat: Add fetch webpage tool [LET-4188] (#4395) 
* Add fetch webpage tool

* Use trafilatura for web extraction
 2025-09-03 13:34:35 -07:00
Matthew Zhou
6e633bd8f9 feat: Change namespace to be org scoped and filter on agent_id [LET-4163] (#4368) 
* Change to org scoped and agent_id filtering

* Finish modifying conversation search tool

* Fix failing tests

* Get rid of bad imports
 2025-09-03 10:00:19 -07:00
Charles Packer
361c50bce4 fix: patch context window of gpt-5 to 272k not 400k [LET-4177] (#4379) 
fix: patch context window of gpt-5 to 272k not 400k
 2025-09-02 21:10:40 -07:00
Sarah Wooders
891da984a6 fix: fix various ease of use problems (#3934) 
Co-authored-by: Matt Zhou <mattzh1314@gmail.com>
 2025-08-15 00:07:12 -07:00
cthomas
aab41cdb76 feat: add agent id input validation in retrieve endpoint (#3892) 2025-08-13 14:03:05 -07:00
Charles Packer
c02bff1e9b fix: patch gpt-5 max context window in constants (#3843) 2025-08-10 14:55:22 -07:00
Matthew Zhou
76c9a58d6f feat: Support streaming and move endpoint for letta-free (#3780) 2025-08-06 15:33:35 -07:00
Kevin Lin
ec04ca99f7 feat: exclude stronger models from default base tool rules (#3703) 
Co-authored-by: Sarah Wooders <sarahwooders@gmail.com>
 2025-08-05 20:33:05 +00:00
Matthew Zhou
e62ddf8355 feat: Add per-agent file management controls with context-aware defaults (#3467) 2025-07-22 10:43:37 -07:00
Matthew Zhou
33d99be157 feat: Add env var to control model within builtin web_search tool (#3417) 2025-07-18 16:45:59 -07:00
Matthew Zhou
d0d67d8b9b feat: Throttle pinecone uploads (#3373) 2025-07-16 20:29:08 -07:00
Matthew Zhou
da17351ca4 feat: Add throttling and retries for pinecone (#3302) 2025-07-14 10:30:49 -07:00
Matthew Zhou
3959f8ba74 feat: Add batching to record upsert (#3196) 2025-07-07 12:18:39 -07:00
Matthew Zhou
954675396f feat: Add pinecone for cloud embedding (#3160) 2025-07-03 22:37:55 -07:00
Andy Li
33c1f26ab6 feat: support for agent loop job cancelation (#2837) 2025-07-02 14:31:16 -07:00
Matthew Zhou
243d3d040b feat: Add close all files functionality (#3139) 2025-07-02 14:27:38 -07:00
Matthew Zhou
efca9d8ea0 feat: Only add suffix on duplication (#3120) 2025-07-01 13:48:38 -07:00
Kevin Lin
a6b991df93 feat: increase default file block size (#3074) 2025-06-30 10:59:30 -07:00