phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

fix(tools): do not index tools, only index toolgroups (#2261)

Browse source 
When registering a MCP endpoint, we cannot list tools (like we used to)
since the MCP endpoint may be behind an auth wall. Registration can
happen much sooner (via run.yaml).

Instead, we do listing only when the _user_ actually calls listing.
Furthermore, we cache the list in-memory in the server. Currently, the
cache is not invalidated -- we may want to periodically re-list for MCP
servers. Note that they must call `list_tools` before calling
`invoke_tool` -- we use this critically.

This will enable us to list MCP servers in run.yaml

## Test Plan

Existing tests, updated tests accordingly.
This commit is contained in:
Ashwin Bharambe 2025-05-25 13:27:52 -07:00 • committed by GitHub
parent 5a422e236c
commit ce33d02443
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
19 changed files with 131 additions and 153 deletions
Download patch file Download diff file Expand all files Collapse all files

7
tests/integration/tool_runtime/test_builtin_tools.py
View file

@ -25,10 +25,12 @@ def test_web_search_tool(llama_stack_client, sample_search_query):
if "TAVILY_SEARCH_API_KEY" not in os.environ:
pytest.skip("TAVILY_SEARCH_API_KEY not set, skipping test")
tools = llama_stack_client.tool_runtime.list_tools()
assert any(tool.identifier == "web_search" for tool in tools)
response = llama_stack_client.tool_runtime.invoke_tool(
tool_name="web_search", kwargs={"query": sample_search_query}
)
# Verify the response
assert response.content is not None
assert len(response.content) > 0
@ -49,11 +51,12 @@ def test_wolfram_alpha_tool(llama_stack_client, sample_wolfram_alpha_query):
if "WOLFRAM_ALPHA_API_KEY" not in os.environ:
pytest.skip("WOLFRAM_ALPHA_API_KEY not set, skipping test")
tools = llama_stack_client.tool_runtime.list_tools()
assert any(tool.identifier == "wolfram_alpha" for tool in tools)
response = llama_stack_client.tool_runtime.invoke_tool(
tool_name="wolfram_alpha", kwargs={"query": sample_wolfram_alpha_query}
)
print(response.content)
assert response.content is not None
assert len(response.content) > 0
assert isinstance(response.content, str)