chore: Stack server no longer depends on llama-stack-client (#4094)

This dependency has been bothering folks for a long time (cc @leseb). We
really needed it due to "library client" which is primarily used for our
tests and is not a part of the Stack server. Anyone who needs to use the
library client can certainly install `llama-stack-client` in their
environment to make that work.

Updated the notebook references to install `llama-stack-client`
additionally when setting things up.

tests/integration/tool_runtime/test_mcp.py

@@ -10,7 +10,7 @@ import pytest
 from llama_stack_client.lib.agents.agent import Agent
 from llama_stack_client.lib.agents.turn_events import StepCompleted, StepProgress, ToolCallIssuedDelta
 
-from llama_stack import LlamaStackAsLibraryClient
+from llama_stack.core.library_client import LlamaStackAsLibraryClient
 
 AUTH_TOKEN = "test-token"
 

tests/integration/tool_runtime/test_mcp_json_schema.py

@@ -13,7 +13,7 @@ import json
 
 import pytest
 
-from llama_stack import LlamaStackAsLibraryClient
+from llama_stack.core.library_client import LlamaStackAsLibraryClient
 from tests.common.mcp import make_mcp_server
 
 AUTH_TOKEN = "test-token"

tests/integration/tool_runtime/test_registration.py

@@ -8,8 +8,8 @@ import re
 
 import pytest
 
-from llama_stack import LlamaStackAsLibraryClient
 from llama_stack.apis.common.errors import ToolGroupNotFoundError
+from llama_stack.core.library_client import LlamaStackAsLibraryClient
 from tests.common.mcp import MCP_TOOLGROUP_ID, make_mcp_server