forked from phoenix-oss/llama-stack-mirror
# Problem
Our current Agent framework has discrepancies in definition on how we
handle server side and client side tools.
1. Server Tools: a single Turn is returned including `ToolExecutionStep`
in agenst
2. Client Tools: `create_agent_turn` is called in loop with client agent
lib yielding the agent chunk
|
||
---|---|---|
.. | ||
tests | ||
__init__.py | ||
agent_instance.py | ||
agents.py | ||
config.py | ||
persistence.py | ||
safety.py |