Fimeg/letta-server
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity
6,229 Commits 1 Branch 0 Tags
d09f321af7e11fa4e0dcb2b87c4fa4e71b3659be
Commit Graph

64 Commits

Author SHA1 Message Date
cthomas
4823416af9 feat: default unpack assistant message content [LET-5404] (#5707) 
feat: default unpack assistant message content
 2025-10-24 15:14:20 -07:00
cthomas
73dcc0d4b7 feat: latest hitl + parallel tool call changes (#5565) 2025-10-24 15:12:49 -07:00
Matthew Zhou
643ec8fe2f fix: Double write tool call deltas [LET-5545] (#5461) 
* Double write tool call deltas

* Fix
 2025-10-24 15:12:11 -07:00
Kevin Lin
08da1a64bb feat: parse reasoning_content from OAI proxies (eg. vLLM / OpenRouter) (#5372) 
* reasonig_content support

* fix

* comment

* fix

* rm comment

---------

Co-authored-by: Charles Packer <packercharles@gmail.com>
 2025-10-24 15:11:31 -07:00
Kian Jones
c2e474e03a feat: refactor logs to parse as a single log line each and filter out 404s from sentry (#5242) 
* add multiline log auto detect

* implement logger.exception()

* filter out 404

* remove potentially problematic changes
 2025-10-24 15:11:31 -07:00
Matthew Zhou
7511b0f4fe feat: Write anthropic streaming interface that supports parallel tool calling [LET-5355] (#5295) 
Write anthropic streaming interface that supports parallel tool calling
 2025-10-09 15:25:21 -07:00
Matthew Zhou
5593f1450b feat: Double write to ToolCallMessage's new list tool_calls field (#5268) 
* Add new tool_calls field to ToolCallMessage

* fern autogen

* Double write to new tool_calls field

* Update straggling instances
 2025-10-09 13:20:52 -07:00
cthomas
cc913df27c feat: add signature to content parts (#5134) 
* feat: add signature to content parts

* always base64 encode thought signature

* propagate thought signature back to request
 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
3e17b4289a feat: gracefully handle gemini empty content parts (#5116) 2025-10-07 17:50:48 -07:00
cthomas
f7755d837a feat: add gemini streaming to new agent loop (#5109) 
* feat: add gemini streaming to new agent loop

* add google as required dependency

* support storing all content parts

* remove extra google references
 2025-10-07 17:50:48 -07:00
Sarah Wooders
ef07e03ee3 feat: add run_id to input messages and step_id to messages (#5099) 2025-10-07 17:50:48 -07:00
cthomas
a3545110cf feat: add full responses api support in new agent loop (#5051) 
* feat: add full responses api support in new agent loop

* update matrix in workflow

* relax check for reasoning messages for high effort gpt 5

* fix indent

* one more relax
 2025-10-07 17:50:48 -07:00
cthomas
67f8e46619 feat: add run id to streamed messages (#5037) 2025-10-07 17:50:47 -07:00
cthomas
f235dfb356 feat: add tool call test for new agent loop (#5034) 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
cthomas
cb7296c81d fix: approval request for streaming (#4445) 
* fix: approval request for streaming

* fix: claude code attempt, unit test passing (add on to #4445) (#4448)

* fix: claude code attempt, unit test passing

* chore: update locks to 0.1.314 from 0.1.312

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

* chore: drop dead poetry lock

---------

Co-authored-by: Charles Packer <packercharles@gmail.com>
 2025-09-05 17:43:21 -07:00
Charles Packer
264171f327 fix: patch streaming hidden reasoning event [LET-4167] (#4367) 
* fix: patch streaming hidden reasoning event

* fix: patch reasoning_effort not getting passed to openai
 2025-09-02 16:21:18 -07:00
Charles Packer
9d49eff204 fix: patch the streaming issue in the openai client for when inner_thoughts_in_kwargs is off [LET-4146] (#4350) 
fix: patch the streaming issue in the openai client for when inner_thoughts_in_kwargs is off
 2025-09-02 12:44:25 -07:00
Charles Packer
e741f84add fix: patch bug w/ extended thinking mode involving text leaking into reasoning (#4341) 
* fix: patch for bad native reasoning behavior w/ sonnet

* fix: cleanup

* fix: cleanup

* fix: another prompt tune for less flaking
 2025-09-01 20:26:24 -07:00
cthomas
1edcc13778 feat: support filtering out messages when converting to openai dict (#4337) 
* feat: support filtering out messages when converting to openai dict

* fix imports
 2025-09-01 12:48:45 -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
c8b370466e fix: duplicate message stream error (#3834) 2025-08-11 14:27:35 -07:00
cthomas
db41f01ac2 feat: continue stream processing on client cancel (#3796) 2025-08-07 13:17:36 -07:00
Andy Li
ca6f474c4e feat: track metrics for runs in db 2025-08-06 15:46:50 -07:00
cthomas
7d33254f5f feat: log stream cancellation to sentry (#3759) 2025-08-05 16:07:30 -07:00
jnjpng
6b082f0447 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
Andy Li
33c1f26ab6 feat: support for agent loop job cancelation (#2837) 2025-07-02 14:31:16 -07:00
Kevin Lin
868294533c feat: add omitted reasoning to streaming openai reasoning (#2846) 
Co-authored-by: Charles Packer <packercharles@gmail.com>
 2025-06-24 18:47:38 -07:00
Matthew Zhou
0c2a80d69b feat: Integrate tool executor into VoiceAgent (#2872) 2025-06-17 14:55:58 -07:00
Sarah Wooders
5fa52a2c38 fix: avoid calling model_dump on stop reason messages twice (#2811) 2025-06-13 18:25:35 -07:00
cthomas
1405464a1c feat: send stop reason in letta APIs (#2789) 2025-06-13 16:04:48 -07:00
Andy Li
33bfd14017 fix: metric tracking (#2785) 2025-06-13 13:53:10 -07:00
cthomas
605a1f410c feat: consolidate logic for finish tokens (#2779) 2025-06-12 15:24:06 -07:00
Kevin Lin
58c4448235 fix: patch reasoning models (#2703) 
Co-authored-by: Charles Packer <packercharles@gmail.com>
 2025-06-11 17:20:04 -07:00
Matthew Zhou
881506d574 fix: Turn off parallel tool calling for Claude (#2736) 2025-06-10 13:04:20 -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
22c66da7bc fix: add temp hack to gracefully handle parallel tool calling (#2654) 2025-06-05 14:43:46 -07:00
cthomas
6d094fd196 fix: send message tests (#2656) 2025-06-05 13:57:43 -07:00
cthomas
da49024a5a fix: inner thoughts kwarg should never be streamed (#2644) 2025-06-05 12:30:55 -07:00
Kevin Lin
0d6907c8cf fix: set openai streaming interface letta_message_id (#2648) 
Co-authored-by: Caren Thomas <carenthomas@gmail.com>
 2025-06-05 12:26:01 -07:00
cthomas
904ccd65b6 fix: remove separate tool call id in streaming path (#2641) 2025-06-04 17:35:55 -07:00
cthomas
a8f394d675 feat: populate tool call name and id in when token streaming (#2639) 2025-06-04 17:06:44 -07:00
Matthew Zhou
7debadb3b9 fix: Change enum to fix composio tests (#2488) 2025-05-28 10:24:22 -07:00
Matthew Zhou
dba4cc9ea0 feat: Add TTFT latency from provider in traces (#2481) 2025-05-28 10:06:16 -07:00
cthomas
871e171b44 feat: add tracing to streaming interface (#2477) 2025-05-27 16:20:05 -07:00
Matthew Zhou
ad6e446849 feat: Asyncify insert archival memories (#2430) 
Co-authored-by: Caren Thomas <carenthomas@gmail.com>
 2025-05-25 22:28:35 -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