phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 09:53:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: Update import path after API reorganization

Browse source 
- Fixed broken import in openai_responses.py validation code
  Changed: llama_stack.apis.agents.openai_responses → llama_stack_api.openai_responses
- Removed unnecessary skip from test_mcp_tools_in_inference
  Test already has proper client type check (LlamaStackAsLibraryClient)
  The library client DOES have register_tool_group() method
This commit is contained in:
Omar Abdelwahab 2025-11-13 15:49:20 -08:00
parent c2bf725a77
commit b5395fa5d3
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/llama_stack/providers/inline/agents/meta_reference/responses/openai_responses.py
View file

@ -259,7 +259,7 @@ class OpenAIResponsesImpl:
# Validate MCP tools: ensure Authorization header is not passed via headers dict # Validate MCP tools: ensure Authorization header is not passed via headers dict
if tools: if tools:
from llama_stack.apis.agents.openai_responses import OpenAIResponseInputToolMCP from llama_stack_api.openai_responses import OpenAIResponseInputToolMCP
for tool in tools: for tool in tools:
if isinstance(tool, OpenAIResponseInputToolMCP) and tool.headers: if isinstance(tool, OpenAIResponseInputToolMCP) and tool.headers: