Ari Webb
89c7ab5f14
feat: structured outputs for openai [LET-6233] ( #6363 )
...
* first hack with test
* remove changes integration test
* Delete apps/core/tests/sdk_v1/integration/integration_test_send_message_v2.py
* add test
* remove comment
* stage and publish api
* deprecate base level response_schema
* add param to llm_config test
---------
Co-authored-by: Ari Webb <ari@letta.com >
2025-11-26 14:39:39 -08:00
Ari Webb
ce2ca8660b
feat: add effort dropdown for claude 4.5 opus (backend) ( #6351 )
...
* feat: add effort support (backend)
* fix test_agent_state_schema_unchanged
---------
Co-authored-by: Ari Webb <ari@letta.com >
2025-11-24 19:10:27 -08:00
Ari Webb
699820cecd
fix: managers test ( #6232 )
...
fix managers test
Co-authored-by: Ari Webb <ari@letta.com >
2025-11-24 19:09:33 -08:00
Ari Webb
b0f9986209
feat: make letta_v1_agent default [LET-6153] ( #6115 )
...
* agent change
* fix tests
* fix more tests
* memgpt_v2_agent for cloud-api tests
---------
Co-authored-by: Ari Webb <ari@letta.com >
2025-11-24 19:09:33 -08:00
Shelley Pham
b73545cd60
fix: agents created from templates cannot read attached files [LET-6146] ( #6137 )
...
* fix: Ensure agents created from templates can read attached files
* test: Add test for template-based agent file attachment from sources
2025-11-13 15:36:56 -08:00
Sarah Wooders
982501f6fa
feat: create model table to persist available models ( #5835 )
...
---------
Co-authored-by: Ari Webb <arijwebb@gmail.com >
Co-authored-by: Ari Webb <ari@letta.com >
2025-11-13 15:36:56 -08:00
Ari Webb
f36845b485
feat: add create memory for archive [LET-6148] ( #6110 )
...
* first hack
* add to stainless
* renaming field
---------
Co-authored-by: Ari Webb <ari@letta.com >
2025-11-13 15:36:56 -08:00
Sarah Wooders
6eeb3c90bb
feat: bring back model_settings and remove validation again ( #6104 )
2025-11-13 15:36:56 -08:00
Sarah Wooders
ddc87418f4
feat: revert model_settings ( #6089 )
2025-11-13 15:36:56 -08:00
Sarah Wooders
0b1fe096ec
feat: split up handle and model_settings ( #6022 )
2025-11-13 15:36:56 -08:00
Christina Tong
c76bc9e216
feat: add filters to count_agents endpoint [LET-5380] [LET-5497] ( #6008 )
...
* feat: add filters to count_agents endpoint [LET-5380]
* comment
* update
2025-11-13 15:36:55 -08:00
jnjpng
849d0dc64a
feat: provider-specific model configuration ( #5873 ) ( #5874 )
2025-11-13 15:36:55 -08:00
Christina Tong
881831501a
feat: filter list agents by stop reason [LET-5928] ( #5779 )
...
* feat: add last_stop_reason to AgentState [LET-5911]
* feat: filter list agents by stop reason [LET-5928]
* undo agent loop changes, use update_run_by_id_async
* add run manager test
* add integration tests
* remove comment
* fix duplicate
* fix docs
2025-11-13 15:36:55 -08:00
Christina Tong
ef3df907c5
feat: add last_stop_reason to AgentState [LET-5911] ( #5772 )
...
* feat: add last_stop_reason to AgentState [LET-5911]
* undo agent loop changes, use update_run_by_id_async
* add run manager test
* add integration tests
* remove comment
* remove duplicate test
2025-11-13 15:36:55 -08:00
Kian Jones
60115d4931
fix: lettuce import and add unit tests for new run manager function ( #5893 )
...
* fix lettuce import and add unit tests for new run manager function
* fix unit tests
* bump version (unrelated)
2025-11-13 15:36:38 -08:00
Sarah Wooders
cfeed463a9
Revert "feat: provider-specific model configuration " ( #5873 )
...
Revert "feat: provider-specific model configuration (#5774 )"
This reverts commit 34a334949a3ef72cd49ff0ca3da9e85d16daa57c.
2025-11-13 15:36:20 -08:00
Sarah Wooders
aaa12a393c
feat: provider-specific model configuration ( #5774 )
...
* initial code updates
* add models
* cleanup
* support overriding
* add apis
* cleanup reasoning interfaces to match models
* update schemas
* update apis
* add new field
* remove parallel
* various fixes
* modify schemas
* fix
* fix
* make model optional
* undo model schema change
* update schemas
* update schemas
* format
* fix tests
* attempt to patch web
* fic docs
* change schemas
* update error
* fix tests
* delete tests
* clean up undefined matching conditional
---------
Co-authored-by: jnjpng <jin@letta.com >
Co-authored-by: Letta Bot <noreply@letta.com >
2025-11-13 15:36:14 -08:00
Sarah Wooders
6654473514
fix: handle block race conditions ( #5819 )
2025-11-13 15:36:14 -08:00
Shubham Naik
95816b9b28
Shub/let 5962 add perfomranceduration search to runs [LET-5962] ( #5850 )
...
* feat: add perfomrance/search to list internal runs
* chore: add tests
* chore: fix ui
* feat: support UI for this
* chore: update tests
* chore: update types
---------
Co-authored-by: Shubham Naik <shub@memgpt.ai >
2025-11-13 15:36:14 -08:00
Sarah Wooders
24a14490d8
fix: add more error logging and tests for streaming LLM errors ( #5844 )
2025-11-13 15:36:14 -08:00
Kian Jones
60226ad203
fix: missing cursor kwargs ( #5763 )
...
* accept cursor logic
* add test
2025-11-13 15:35:34 -08:00
Kian Jones
1059452c11
fix: expect raise on detach to deleted agent ( #5770 )
...
just expect raise
2025-11-13 15:35:34 -08:00
Christina Tong
5fddf94ac3
fix: pagination broken in runs table [LET-5790] ( #5759 )
...
* fix: pagination broken in runs table [LET-5790]
* update pagination test
* fix test
2025-11-13 15:35:34 -08:00
jnjpng
6e2c002af3
feat: add stainless pagination for top level arrays with order by [LET-5800] ( #5687 )
...
* base
* revert openapi
* union
* simplify
* stainless
* stainless
* fix
* fix test
* generate
---------
Co-authored-by: Letta Bot <noreply@letta.com >
2025-10-24 15:14:31 -07:00
Matthew Zhou
e7e86124f9
feat: Support embedding config on the archive [LET-5832] ( #5714 )
...
* Add embedding config field to archives
* Fix alembic script
* Simplify archive manager
* Fern autogen
* Fix failing tests
* Fix alembic
2025-10-24 15:14:21 -07:00
Matthew Zhou
69343bf5f2
feat: Add delete endpoint [LET-4400] ( #5711 )
...
* Add delete endpoint
* Fern autogen
2025-10-24 15:14:20 -07:00
Ari Webb
6b5c3a7130
feat: list_agents_for_archive endpoint [LET-4407] ( #5684 )
...
* list_archives_for_agent
* use pattern from blocks instead
* use new parameter include
---------
Co-authored-by: Ari Webb <ari@letta.com >
2025-10-24 15:14:20 -07:00
cthomas
afdf0f80e3
feat: add backend support for agent relationship loads ( #5693 )
2025-10-24 15:14:09 -07:00
Ari Webb
e54df7f3a4
feat: add attach and detach archive to agent [LET-4402] ( #5679 )
...
* add attach and detach
Co-authored-by: Ari Webb <ari@letta.com >
2025-10-24 15:13:47 -07:00
cthomas
c3c38f2713
feat: rename multi agent group to managed group [LET-5799] ( #5672 )
...
feat: rename multi agent group to managed group
2025-10-24 15:13:47 -07:00
cthomas
14faa27869
feat: replace agent.identity_ids with agent.identities [LET-5803] ( #5673 )
...
feat: replace agent.identity_ids with agent.identities
2025-10-24 15:13:47 -07:00
Kian Jones
45065297a0
feat: runtime validation for ids for internal managers calls ( #5544 )
...
* claude coded first pass
* fix test cases to expect errors instead
* fix this
* let's see how letta-code did
* claude
* fix tests, remove dangling comments, retrofit all managers functions with decorator
* revert to main for these since we are not erroring on invalid tool and block ids
* reorder decorators
* finish refactoring test cases
* reorder agent_manager decorators and fix test tool manager
* add decorator on missing managers
* fix id sources
* remove redundant check
* uses enum now
* move to enum
2025-10-24 15:13:47 -07:00
cthomas
0a083459c6
feat: add new blocks field to agent state schema test ( #5668 )
2025-10-24 15:13:47 -07:00
Christina Tong
12185c8601
feat: add tools used filtering to internal runs [LET-5415] ( #5557 )
...
* feat: add tool_used field to run_metrics [LET-5419]
* change to tool name
* use tool ids over names
* feat: add internal runs route with template_family filtering
* feat: add step count filtering to internal runs [LET-5417]
* remove import
* add auto generated
* feat: add tools used filtering to internal runs [LET-5415]
* add test
* add test
* fix snippets
2025-10-24 15:13:47 -07:00
Christina Tong
77c797c752
feat: add step count filtering to internal runs [LET-5417] ( #5547 )
...
* feat: add tool_used field to run_metrics [LET-5419]
* change to tool name
* use tool ids over names
* feat: add internal runs route with template_family filtering
* feat: add step count filtering to internal runs [LET-5417]
* remove import
* add auto generated
* add test
* fix snippets
2025-10-24 15:13:47 -07:00
Christina Tong
44574ec264
feat: add internal runs route with template_family filtering [LET-5416] ( #5543 )
...
* feat: add tool_used field to run_metrics [LET-5419]
* change to tool name
* use tool ids over names
* feat: add internal runs route with template_family filtering
* remove import
* add auto generated
* restrict internal runs
* add test, address comments
* add docs and auto generated fields
* remove unused template mixins
* update openapi
* add generated
2025-10-24 15:13:15 -07:00
jnjpng
8275bdd7e3
feat: add agent state schema change test ( #5573 )
...
base
Co-authored-by: Letta Bot <noreply@letta.com >
2025-10-24 15:13:15 -07:00
jnjpng
b3fef4b5a8
feat: double write to all encrypted columns and decrypt on read ( #5265 )
...
* base
* use secret field
* fix
* auth code
* stage publish
* decouple backfill
* revert uncomment
* providers and agent vars
* mcp
* mcp
* stage and publish
* fix oauth
* double encrypt
* sandbox
---------
Co-authored-by: Letta Bot <noreply@letta.com >
2025-10-24 15:11:31 -07:00
Matthew Zhou
609e63cb12
feat: Adjust message conversion to support multiple tool calls [LET-5336] ( #5270 )
...
* Adjust message conversion
* Make collection logic cleaner
2025-10-09 13:20:52 -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
Shelley Pham
346db5ce60
feat: add status to runs api [PRO-1529] ( #5214 )
2025-10-07 17:50:50 -07:00
Matthew Zhou
126e51d584
feat: Support returning multiple tool returns [LET-4678] ( #5202 )
...
* Support returning multiple tool returns
* Fix test run managers
2025-10-07 17:50:50 -07:00
Sarah Wooders
7aff9aa659
feat: error handling for rest api for agents + blocks [LET-4625] ( #5142 )
2025-10-07 17:50:49 -07:00
Sarah Wooders
7b73b25a95
fix: fix mcp for complex schemas and add tests ( #5063 )
2025-10-07 17:50:48 -07:00
Sarah Wooders
354205f581
feat: create new runs table [LET-4467] ( #4841 )
2025-10-07 17:50:47 -07:00
Sarah Wooders
d0d36a4b07
fix: remove json schema generation from tool validation [LET-4509] ( #4964 )
...
* patch integration test
* create default user and org
* rm
* patch
* add testing
* remove validation for schemas from pydantic object
* add file
* patch tests
* fix more tests
* fix managers
* fix sdk test
* patch schema tests
* Comment out name in update
* patch test
* patch
* add another test
2025-10-07 17:50:46 -07:00
Matthew Zhou
6d71a606aa
test: Test archive manager thoroughly ( #4955 )
...
Test archive manager thoroughly
2025-10-07 17:50:46 -07:00
Sarah Wooders
53786ee102
feat: asyncify test_manager.py [LET-4494] ( #4890 )
...
* add test_agent_manager.py
* created shared conftest
* add test_tool_manager.py
* add tag tests
* add message manager tests
* add blocks
* add org
* add passage tests
* add archive manager
* add user manager
* add identity
* add job manager tests
* add sandbox manager
* add file manager
* add group managers
* add mcp manager
* fix batch tests
* update workflows
* fix test_managers.py
* more tests
* comment out old test and add file
---------
Co-authored-by: Matthew Zhou <mattzh1314@gmail.com >
2025-10-07 17:50:46 -07:00
