Kian Jones
077d0e2f9a
feat: dump stack trace on segfault ( #6121 )
...
* dump stack trace on segfault
* log tokenizer
2025-11-13 15:36:56 -08:00
jnjpng
6139ab23d2
fix: v1 sdk send message tests for message union rename ( #6123 )
...
* add
* base:
---------
Co-authored-by: Letta Bot <noreply@letta.com >
2025-11-13 15:36:56 -08:00
Sarah Wooders
d37ed2e056
fix: patch update model settings ( #6118 )
2025-11-13 15:36:56 -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
Christina Tong
2a8523aa01
chore: migrate multi agent integration test to v1 sdk [LET-6152] ( #6113 )
...
* chore: migrate multi agent integration test to v1 sdk [LET-6152]
* update functions
* access field
* clean
* flexibility for in context messge
* add agent type
* check content
* update
* agent type
2025-11-13 15:36:56 -08:00
Kian Jones
7b7b89ecfa
fix: fix alembic on main ( #6116 )
...
fix alembic on main
2025-11-13 15:36:56 -08:00
Kian Jones
78600fac23
chore: index suggestions from planetscale suggestions ( #6111 )
...
suggestions from ps dashboard
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
Cameron
bd5f684346
Update archival memory docstrings for clarity ( #6098 )
...
* Update archival memory docstrings for clarity
Improved docstrings for archival_memory_insert and archival_memory_search to:
- Better explain when and how to use these tools
- Provide clearer best practices
- Include more realistic examples (meeting notes, project updates)
- Emphasize semantic search vs keyword matching
- Clarify tag filtering behavior
👾 Generated with [Letta Code](https://letta.com )
Co-Authored-By: Letta <noreply@letta.com >
* examples
---------
Co-authored-by: Letta <noreply@letta.com >
Co-authored-by: Kevin Lin <kl2806@columbia.edu >
2025-11-13 15:36:56 -08:00
Kian Jones
e665768085
chore: alembic upgrade for step metrics run id index ( #6109 )
...
alembic upgrade for step metrics run id index
2025-11-13 15:36:56 -08:00
cthomas
284201f6f8
feat: use new agent loop when messaging sleeptime directly ( #6107 )
2025-11-13 15:36:56 -08:00
Sarah Wooders
ddc87418f4
feat: revert model_settings ( #6089 )
2025-11-13 15:36:56 -08:00
cthomas
bbffadc245
chore: api sync for health endpoint ( #6088 )
...
chore: api sync
2025-11-13 15:36:56 -08:00
cthomas
c0f270047c
feat: add list support for query params in sdk ( #6085 )
...
* feat: add list support for query params in sdk
* use repeat array_format
* use dots for nested_format
2025-11-13 15:36:56 -08:00
Shubham Naik
eb0e03d7bb
chore: move v1health to async [LET-6125] ( #6086 )
...
* chore: move v1health to async
* chore: make async
---------
Co-authored-by: Shubham Naik <shub@memgpt.ai >
2025-11-13 15:36:56 -08:00
Kian Jones
d360242307
fix: don't expect stop reason to have a run id ( #6083 )
...
don't expect stop reason to have a run id
2025-11-13 15:36:56 -08:00
Kian Jones
ba19142669
fix: address high query latency with step id index on messages ( #6068 )
...
* add step id index on messages
* simple index
* fix sources padding
* fix import
* fix passage manager
* fix ci
* I think fixed
* disable turbopufer for managers to avoid failing passages tests
2025-11-13 15:36:56 -08:00
Charles Packer
081a1f6920
fix(core): patch responses api parallel tool calling not returning tool call IDs ( #6079 )
...
* fix(core): patch responses api parallel tool calling not returning tool call ids
* fix(core): patch chatcompletions as well
* fix: patch problem with gpt-4.1
2025-11-13 15:36:56 -08:00
Kian Jones
814856711e
fix: prevent too many runs bug ( #6076 )
...
* add limit of 1000 and change FE
* add safety
* const name
* update limit
* add max limit
---------
Co-authored-by: christinatong01 <christina@letta.com >
2025-11-13 15:36:56 -08:00
Charles Packer
2e721ddc62
fix: various hardening to prevent stale state on background mode runs ( #6072 )
...
fix: various hardening to prevent stale state on backgroun
d mode runs
2025-11-13 15:36:56 -08:00
jnjpng
744fa6ae03
feat: add model settings schema to stainless [LET-5976] ( #5872 )
...
* base
* test
* test
* update
* update
* generate
* regen
* update
* fix
* push
---------
Co-authored-by: Letta Bot <noreply@letta.com >
2025-11-13 15:36:56 -08:00
jnjpng
5797b4162e
fix: agent create test + stage publish api ( #6063 )
...
* base
* fix
---------
Co-authored-by: Letta Bot <noreply@letta.com >
2025-11-13 15:36:56 -08:00
Shubham Naik
9534ee23be
chore; regen ( #6067 )
...
Co-authored-by: Shubham Naik <shub@memgpt.ai >
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
Sarah Wooders
19e6b09da5
docs: remove schemas from docstrings ( #6059 )
2025-11-13 15:36:56 -08:00
jnjpng
cb63753db6
fix: f string formatting separator in anthropic client ( #6058 )
...
* fix
* fix
---------
Co-authored-by: Letta Bot <noreply@letta.com >
2025-11-13 15:36:56 -08:00
jnjpng
5e35887295
fix: tools page not subscriptable ( #6057 )
...
fix
Co-authored-by: Letta Bot <noreply@letta.com >
2025-11-13 15:36:56 -08:00
jnjpng
a66a8187cd
fix: v1 sdk tests directly subscripting from list endpoints ( #6054 )
...
* base
* fix
* fix
* runs
* skip
---------
Co-authored-by: Letta Bot <noreply@letta.com >
2025-11-13 15:36:56 -08:00
Sarah Wooders
483a97ee77
docs: add migration guide [LET-6085] ( #6006 )
...
* add migration guide
* update mcp
2025-11-13 15:36:55 -08:00
jnjpng
edbff34d63
feat: enable streaming flag on send message [LET-6100] ( #6040 )
...
* base
* base
* update
* stainless
* final
---------
Co-authored-by: Letta Bot <noreply@letta.com >
2025-11-13 15:36:55 -08:00
Kian Jones
789f6cf9cd
feat: log incoming requests too ( #6050 )
...
log incoming requests too
2025-11-13 15:36:55 -08:00
Ari Webb
526a678f8c
fix: fix agent test, returns new data format ( #6039 )
...
fix conftest
Co-authored-by: Ari Webb <ari@letta.com >
2025-11-13 15:36:55 -08:00
Charles Packer
18029250d0
fix(core): sanitize messages to anthropic in the main path the same way (or similar) to how we do it in the token counter ( #6044 )
...
* fix(core): sanitize messages to anthropic in the main path the same way (or similar) to how we do it in the token counter
* fix: also patch poison error in backend by filtering lazily
* fix: remap streaming errors (what the fuck)
* fix: dedupe tool clals
* fix: cleanup, removed try/catch
2025-11-13 15:36:55 -08:00
Charles Packer
363a5c1f92
fix: fix poison state from bad approval response ( #5979 )
...
* fix: detect and fail on malformed approval responses
* fix: guard against None approvals in utils.py
* fix: add extra warning
* fix: stop silent drops in deserialize_approvals
* fix: patch v3 stream error handling to prevent sending end_turn after an error occurs, and ensures stop_reason is always set when an error occurs
* fix: Prevents infinite client hangs by ensuring a terminal event is ALWAYS sent
* fix: Ensures terminal events are sent even if inner stream generator fails to
send them
2025-11-13 15:36:55 -08:00
Kian Jones
4acda9c80f
feat: global exception middleware ( #6017 )
...
* global exception middleware
* redo both logging middlewares as one
* remove extra middleware files
2025-11-13 15:36:55 -08:00
Kian Jones
a217c8f1b6
fix: re-add embedding dimension padding for archival memories ( #6041 )
...
fix embedding dimension padding
2025-11-13 15:36:55 -08:00
Kian Jones
db6d4bb124
chore: handle tool use id error in anthropic client ( #6016 )
...
handle tool use id error in anthropic client
2025-11-13 15:36:55 -08:00
Kian Jones
dc331c0f61
fix: handle step streaming for sleeptime agent ( #6014 )
...
handle step streaming for sleeptime agent
2025-11-13 15:36:55 -08:00
Kian Jones
e082ad7dec
fix: assorted fixes ( #6003 )
...
* duration fix metrics for temporal, encryption_key in lettuce-py, and v1 sdk bugfix
* none user agent = True
2025-11-13 15:36:55 -08:00
jnjpng
501c325b32
feat: return new Model and EmbeddingModel objects for list model/embedding endpoints [LET-6090] ( #6019 )
...
* base
* generate
* test
* test
* update
* generate
* cypress
---------
Co-authored-by: Letta Bot <noreply@letta.com >
2025-11-13 15:36:55 -08:00
jnjpng
8ff8ef2102
chore: clean up count agent test ( #6037 )
...
base
Co-authored-by: Letta Bot <noreply@letta.com >
2025-11-13 15:36:55 -08:00
Matthew Zhou
8df78e9429
feat: Move file upload to temporal [LET-6089] ( #6024 )
...
* Finish writing temporal upload file activity
* Remove prints
* Rewrite content re-use
2025-11-13 15:36:55 -08:00
Matthew Zhou
940fde24e9
fix: Fix gating for padding again ( #6030 )
...
Fix bool
2025-11-13 15:36:55 -08:00
Matthew Zhou
790e1655e2
fix: Fix circular commit ( #6029 )
...
Fix circular commit
2025-11-13 15:36:55 -08:00
Matthew Zhou
586707a40d
fix: Restore padding except for production ( #6028 )
...
Restore padding except for production
2025-11-13 15:36:55 -08:00
Charles Packer
e8e94f2ebe
fix(core): patch bugs on transcript formatting for sleeptime w/ HITL ( #6025 )
2025-11-13 15:36:55 -08:00
Charles Packer
5beaa84b5f
fix(core): fix enable_sleeptime on letta_agent_v1 getting initial message sequence ( #6018 )
...
fix(core): for letta_agent_v1, if enable_sleeptime, make the sleeptime agent not have initial message sequence, similar to the base agent
2025-11-13 15:36:55 -08:00
Ari Webb
d2fe64bab4
fix: fix parallel tool calling tests in ci [LET-6043] ( #5950 )
...
* first hack
* test
* fix test for v1, comment out for legacy
* test shows parallel tool calling now happening
* fix test to detect parallel tool calling
* update to use oai too
* uncomment v2 test
---------
Co-authored-by: Ari Webb <ari@letta.com >
2025-11-13 15:36:55 -08:00