Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.
merge
Sarah Woodersb1474c8dfa4f
diff --cc letta/__init__.pyindex a662834ec,55b12c31b..161ad0190--- a/letta/__init__.py+++ b/letta/__init__.py@@@ -1,6 -1,6 +1,6 @@@import os- __version__ = "0.8.1"-__version__ = "0.8.0"++__version__ = "0.8.2"if os.environ.get("LETTA_VERSION"):__version__ = os.environ["LETTA_VERSION"]diff --cc letta/server/rest_api/routers/v1/agents.pyindex f13aaa3e3,d0280fa82..4fc29bad1--- a/letta/server/rest_api/routers/v1/agents.py+++ b/letta/server/rest_api/routers/v1/agents.py@@@ -658,9 -665,11 +665,10 @@@ async def send_messageProcess a user message and return the agent's response.This endpoint accepts a message from a user and processes it through the agent."""+ MetricRegistry().user_message_counter.add(1, get_ctx_attributes())+actor = await server.user_manager.get_actor_or_default_async(actor_id=actor_id)request_start_timestamp_ns = get_utc_timestamp_ns()-- user_eligible = True# TODO: This is redundant, remove soonagent = await server.agent_manager.get_agent_by_id_async(agent_id, actor, include_relationships=["multi_agent_group"])agent_eligible = agent.enable_sleeptime or agent.agent_type == AgentType.sleeptime_agent or not agent.multi_agent_groupdiff --cc letta/services/user_manager.pyindex 689704121,eab42743b..a4ad5ac9e--- a/letta/services/user_manager.py+++ b/letta/services/user_manager.py@@@ -9,9 -10,7 +10,8 @@@ from letta.schemas.user import User asfrom letta.schemas.user import UserUpdatefrom letta.server.db import db_registryfrom letta.services.organization_manager import OrganizationManager- from letta.tracing import trace_methodfrom letta.utils import enforce_types+from letta.settings import settingsclass UserManager: