forked from phoenix-oss/llama-stack-mirror
Summary: Fixes AgentConfig init bug introduced with ToolConfig. Namely, the below doesn't work ``` agent_config = AgentConfig( **common_params, tool_config=ToolConfig( tool_choice="required", ), ) ``` bvecause tool_choice was defaulted to 'auto' leading to validation check failing. Test Plan: added unittests LLAMA_STACK_CONFIG=fireworks pytest -s -v tests/client-sdk/ --safety-shield meta-llama/Llama-Guard-3-8B |
||
---|---|---|
.. | ||
client-sdk |