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

13
llama_stack/distribution/routers/tool_runtime.py
View file

@ -11,7 +11,7 @@ from llama_stack.apis.common.content_types import (
InterleavedContent,
)
from llama_stack.apis.tools import (
ListToolDefsResponse,
ListToolsResponse,
RAGDocument,
RAGQueryConfig,
RAGQueryResult,
@ -19,7 +19,8 @@ from llama_stack.apis.tools import (
ToolRuntime,
)
from llama_stack.log import get_logger
from llama_stack.providers.datatypes import RoutingTable
from ..routing_tables.toolgroups import ToolGroupsRoutingTable
logger = get_logger(name=__name__, category="core")
@ -28,7 +29,7 @@ class ToolRuntimeRouter(ToolRuntime):
class RagToolImpl(RAGToolRuntime):
def __init__(
self,
routing_table: RoutingTable,
routing_table: ToolGroupsRoutingTable,
) -> None:
logger.debug("Initializing ToolRuntimeRouter.RagToolImpl")
self.routing_table = routing_table
@ -59,7 +60,7 @@ class ToolRuntimeRouter(ToolRuntime):
def __init__(
self,
routing_table: RoutingTable,
routing_table: ToolGroupsRoutingTable,
) -> None:
logger.debug("Initializing ToolRuntimeRouter")
self.routing_table = routing_table
@ -86,6 +87,6 @@ class ToolRuntimeRouter(ToolRuntime):
async def list_runtime_tools(
self, tool_group_id: str | None = None, mcp_endpoint: URL | None = None
) -> ListToolDefsResponse:
) -> ListToolsResponse:
logger.debug(f"ToolRuntimeRouter.list_runtime_tools: {tool_group_id}")
return await self.routing_table.get_provider_impl(tool_group_id).list_tools(tool_group_id, mcp_endpoint)
return await self.routing_table.list_tools(tool_group_id)