Commit Graph

3157 Commits

Author SHA1 Message Date
Matthew Zhou
5772365285 fix: Fix error messages with malformed gemini call (#3865) 2025-08-11 16:59:19 -07:00
cthomas
639641137d feat: consolidate reasoning model checks (#3862) 2025-08-11 16:55:45 -07:00
cthomas
a9771424fe fix: duplicate message stream error (#3834) 2025-08-11 14:27:35 -07:00
cthomas
32a4ecae9d feat: handle all cases for reasoning toggle (#3857) 2025-08-11 13:45:50 -07:00
Charles Packer
4dcbf0b8f2 fix: patch mcp alerting on sentry 2025-08-11 10:26:42 -07:00
Charles Packer
68974ff882 fix: patch mcp attach bug (#3844) 2025-08-10 17:24:33 -07:00
Charles Packer
60efd98248 fix: patch gpt-5 max context window in constants (#3843) 2025-08-10 14:55:22 -07:00
Charles Packer
722828309c fix: reduce error levels to patch the sentry logging issue (#3835) 2025-08-08 22:15:10 -07:00
Andy Li
63be7417cc chore: clean up tool rule solver code 2025-08-08 16:39:17 -07:00
jnjpng
b62955f0bf fix: gemini 2.5 thinking models fail to call functions if thinking is fully disabled
Co-authored-by: Jin Peng <jinjpeng@Jins-MacBook-Pro.local>
2025-08-08 16:34:32 -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
Kevin Lin
81093ac10b feat: add line number warning to memory_insert (#3829) 2025-08-08 13:47:13 -07:00
Matthew Zhou
b529b1e4fa feat: Add max_steps parameter to agent export (#3828) 2025-08-08 13:38:29 -07:00
cthomas
0d2e2b3f78 fix: reasoning toggle patch (#3826) 2025-08-08 10:42:17 -07:00
Shubham Naik
873bc0348d Revert "feat: add top-level reasoning toggle to ADE (#3813)" (#3825) 2025-08-08 07:44:11 -07:00
Sarah Wooders
e5497b1d0d chore: merge oss (#3712) 2025-08-07 22:20:26 -07:00
jnjpng
9d72955e7f fix: lmstudio tests and integration
Co-authored-by: Jin Peng <jinjpeng@Jins-MacBook-Pro.local>
2025-08-07 20:02:56 -07:00
Kevin Lin
44e4ba91d4 feat: add minimal reasoning effort option to LLMConfig (#3816) 2025-08-07 19:27:32 -07:00
Andy Li
8da571dbd3 chore: remove duplicate tool templating 2025-08-07 18:13:09 -07:00
jnjpng
922c5154e6 feat: add step metrics table
Co-authored-by: Jin Peng <jinjpeng@Jins-MacBook-Pro.local>
2025-08-07 17:51:39 -07:00
cthomas
d062392739 feat: add top-level reasoning toggle to ADE (#3813) 2025-08-07 17:21:12 -07:00
Matthew Zhou
637d2854e6 feat: Change grep to be paginated (#3815) 2025-08-07 16:50:05 -07:00
Sarah Wooders
ce44386011 feat: support opus 4.1 and gpt-5 (#3806) 2025-08-07 15:11:57 -07:00
Sarah Wooders
1ec1bfe312 fix: patch non-optional memory replace (#3803) 2025-08-07 13:51:12 -07:00
cthomas
cab621ac14 feat: continue stream processing on client cancel (#3796) 2025-08-07 13:17:36 -07:00
Sarah Wooders
f02f55bec5 fix: dont have optional argument for memory_replace (#3800) 2025-08-07 10:18:47 -07:00
Matthew Zhou
609bcf84f2 feat: Add comprehensive error tracking to steps table (#3765) 2025-08-06 20:19:29 -07:00
Sarah Wooders
8b1490c879 chore: patch timezone tests (#3789) 2025-08-06 17:24:00 -07:00
cthomas
13c916afaa feat: offload jinja to threadpool LET-3615 (#3787) 2025-08-06 16:34:28 -07:00
Andy Li
33884c358f chore: cleanup workflows for core 2025-08-06 16:01:26 -07:00
Kevin Lin
e20f4eca92 fix: update default include_base_tool_rules to None (#3762)
Co-authored-by: Matthew Zhou <mattzh1314@gmail.com>
2025-08-06 15:58:29 -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
Matthew Zhou
4b788d11de feat: Support streaming and move endpoint for letta-free (#3780) 2025-08-06 15:33:35 -07:00
cthomas
4ca0c82e9c chore: update ci to use min supported python version (#3777) 2025-08-06 15:00:07 -07:00
jnjpng
fcaa6c78a8 fix: fix and update vllm tests
Co-authored-by: Jin Peng <jinjpeng@Jins-MacBook-Pro.local>
Co-authored-by: Kian Jones <kian@letta.com>
2025-08-06 14:37:55 -07:00
cthomas
30b35764a6 chore: modify otel exporter config batch size (#3775) 2025-08-06 13:57:11 -07:00
cthomas
3884d53f81 feat: add signoz integration for otel export (#3772) 2025-08-06 12:06:23 -07:00
cthomas
1957799383 feat: add reasoning toggle in agents routes (#3705) 2025-08-06 11:47:06 -07:00
Charles Packer
985ec7fb18 feat(desktop): allow specifying a remote letta server in the letta desktop (#3709) 2025-08-05 22:21:07 -07:00
cthomas
7efd651366 feat: add ability to specify agent env vars on import (#3753) 2025-08-05 16:36:28 -07:00
cthomas
f3316a0d8a feat: log stream cancellation to sentry (#3759) 2025-08-05 16:07:30 -07:00
Kian Jones
25b1ed48bd chore: Migrate embeddings.memgpt.ai to embeddings.letta.com (#3757) 2025-08-05 15:49:36 -07:00
Kevin Lin
669b54a745 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
a170bd3f7b fix: Fix tool renaming if json schema is passed in (#3745) 2025-08-05 11:36:23 -07:00
Kian Jones
3b092ca843 refactor: simplify docstrings for EmbeddingConfig and LLMConfig classes (#3733)
Co-authored-by: Claude <noreply@anthropic.com>
2025-08-04 16:57:15 -07:00
Andy Li
64d91d6c8a feat: npm requirements for tools 2025-08-04 14:15:10 -07:00
Eric Ly
2927295ee7 feat: add formatting for token sizing (#3631)
Co-authored-by: Eric Ly <lyyeric@letta.com>
2025-08-04 13:54:44 -07:00
cthomas
9c7f01e430 feat: deprecate legacy client (#3726) 2025-08-04 13:36:30 -07:00