Commit Graph

204 Commits

Author SHA1 Message Date
cthomas
6a9eb16f4e feat: add summarization retry to new agent loop (#4477) 2025-09-08 17:41:48 -07:00
cthomas
e06d9cbb8f feat: add error handling parity to new agent loop (#4471) 2025-09-08 16:35:24 -07:00
cthomas
304b8de32a feat: consolidate stream methods for new agent loop (#4468) 2025-09-08 15:20:36 -07:00
Matthew Zhou
531eb6afeb feat: Add project_id to message filtering/inserting to Turbopuffer [LET-4252] (#4466)
* Add project_id

* Fern autogen
2025-09-08 14:35:15 -07:00
cthomas
0360ceeecc feat: add step checkpointing for progress tracking (#4458)
* feat: add step checkpointing for progress tracking

* openapi sync
2025-09-08 10:30:44 -07:00
cthomas
39e4e4227d feat: add agent_step span updates to new agent loop (#4457) 2025-09-06 14:04:01 -07:00
Charles Packer
3442b52cf7 fix(core): patch the error throwing for HITL [LET-4218] (#4455)
fix: patch the error throwing for HITL
2025-09-06 11:45:46 -07:00
cthomas
6029c80446 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
Matthew Zhou
2e3cabc080 feat: Add search messages endpoint [LET-4144] (#4434)
* Add search messages endpoint

* Run fern autogen and fix tests
2025-09-05 14:28:27 -07:00
cthomas
80adb82b34 feat: add provider trace persistence in llm adapters (#4442)
* feat: add provider trace persistence in llm adapters

* hook up to new agent loop
2025-09-05 14:28:20 -07:00
cthomas
59a2245f24 feat: add step progression checkpointing to new agent loop (#4443) 2025-09-05 14:28:06 -07:00
cthomas
20a6e8d65e feat: add project_id to message (#4436) 2025-09-05 11:18:09 -07:00
cthomas
0b7f7e77fb feat: introduce agent loop v3 (#4435) 2025-09-05 11:12:52 -07:00
Matthew Zhou
fcfc40eaf2 feat: Add project id to message schema [LET-4166] (#4433)
* Add project id

* Propogate through update message by id async

* Add project id testing
2025-09-04 16:50:41 -07:00
Matthew Zhou
b8d403c962 feat: Add ranks to archival memory search [LET-4193] (#4426)
* Add ranks to archival memory search

* Fix test managers

* Fix archival memory test
2025-09-04 13:35:54 -07:00
Matthew Zhou
88831c7256 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
e3eb598353 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
cthomas
3f87fc34f2 feat: handle message persistence for approvals flows (#4338) 2025-09-01 14:10:02 -07:00
cthomas
65cd430317 feat: support deny tool call request (#4334) 2025-09-01 10:33:18 -07:00
cthomas
671f561c77 feat: support approve tool call request (#4333) 2025-08-31 11:26:21 -07:00
cthomas
484d2a4e93 feat: add error handling for approval response attempt (#4326)
* feat: add error handling for approval response attempt

* add one more error case

* improve error messages
2025-08-29 20:39:28 -07:00
cthomas
cc376b32ed feat: add support for approval request creation (#4313) 2025-08-29 15:23:02 -07:00
cthomas
bfdb586f74 feat: add approval create input to messages endpoints [LET-4110] (#4309)
* feat: add approval create input to messages endpoints

* rename discriminator tag

* add base class with default

* add field validator

* exclude new type field from agent file schema
2025-08-29 13:16:03 -07:00
Matthew Zhou
23b2769dc4 feat: Allow agent archival tools to insert/search with tags [LET-4072] (#4300)
* Finish modifying archival memory tools

* Add tags

* Add disabled test
2025-08-29 11:55:06 -07:00
Kian Jones
ca6cfa5914 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
Matthew Zhou
651671cb83 feat: Support basic upload/querying on tpuf [LET-3465] (#4255)
* wip implementing turbopuffer

* Move imports up

* Add type of archive

* Integrate turbopuffer functionality

* Debug turbopuffer tests failing

* Fix turbopuffer

* Run fern

* Fix multiple heads
2025-08-28 10:39:16 -07:00
cthomas
b316c61221 feat: add invalid_llm_response stop reason [LET-4083] (#4269)
* feat: add invalid_llm_response stop reason

* add sqllite support

* simply skip for sqllite

* fix imports

* fix isort
2025-08-27 17:07:47 -07:00
cthomas
3d62f14bac feat: add gating to provider trace persistence in db (#4223)
* feat: make provider trace fetch result nullable

* feat: add flag for persisting provider trace to db
2025-08-26 15:58:26 -07:00
Charles Packer
20c1bd316f fix: allow for send_message to be unterminated if the user requests it (#4169) 2025-08-25 21:11:14 -07:00
Sarah Wooders
9eb303b5f4 fix: avoid using summarization agent when not using voice (#4097) 2025-08-25 13:23:24 -07:00
Sarah Wooders
8a1f256c66 fix: add handling for summarizer llm call (#4028) 2025-08-20 16:25:02 -07:00
cthomas
395faf3ed8 feat: add prompt generator for on the fly system prompt generation (#4060) 2025-08-20 15:49:40 -07:00
cthomas
3482c5b371 feat: add null check to step logging LET-3890 (#4004) 2025-08-19 11:52:34 -07:00
cthomas
a518d781e3 fix: tool logging error (#3998) 2025-08-18 18:01:23 -07:00
cthomas
a6528b41d7 feat: set frequency penalty to 1 for gpt-4o (#3962) 2025-08-18 14:20:16 -07:00
jnjpng
5d176b51bb feat: record step metrics to table
Co-authored-by: Jin Peng <jinjpeng@Jins-MacBook-Pro.local>
2025-08-13 11:29:18 -07:00
Andy Li
9805de68ec feat: track run state in stream 2025-08-08 16:31:15 -07:00
jnjpng
a629a9a293 fix: clean up tool execution print statement
Co-authored-by: Jin Peng <jinjpeng@Jins-MacBook-Pro.local>
2025-08-08 15:08:12 -07:00
Matthew Zhou
609bcf84f2 feat: Add comprehensive error tracking to steps table (#3765) 2025-08-06 20:19:29 -07:00
cthomas
13c916afaa feat: offload jinja to threadpool LET-3615 (#3787) 2025-08-06 16:34:28 -07:00
Andy Li
76679e3ecc feat: track metrics for runs in db 2025-08-06 15:46:50 -07:00
cthomas
21f0373b45 feat: remove redundant memory compilation in agent step (#3785) 2025-08-06 15:46:18 -07:00
cthomas
28da313442 chore: deprecate orm enum file (#3724) 2025-08-04 11:59:55 -07:00
Matthew Zhou
25086518cd feat: Implement archival sharing (#3689) 2025-08-01 23:34:49 -07:00
cthomas
8919f06b67 feat: convert compile system prompt to async (#3685) 2025-07-31 15:49:59 -07:00
Andy Li
277c26a58e feat: modal sandbox 2025-07-30 11:25:40 -07:00
jnjpng
7f12230c21 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
Matthew Zhou
2ef90aafc0 feat: Scrub inner thoughts from history on toggle (#3607) 2025-07-28 21:43:36 -07:00
Matthew Zhou
2cd985ef8a fix: Adjust summarize_agent_conversation endpoint to return 204 (#3595) 2025-07-28 14:29:09 -07:00
cthomas
f77a259d07 feat: asyncify jinja templates (#3580) 2025-07-26 23:17:24 -07:00