docs: update test_agents to use new Agent SDK API (#1402)

# Summary:
new Agent SDK API is added in
https://github.com/meta-llama/llama-stack-client-python/pull/178

Update docs and test to reflect this.

Closes https://github.com/meta-llama/llama-stack/issues/1365

# Test Plan:
```bash
py.test -v -s --nbval-lax ./docs/getting_started.ipynb

LLAMA_STACK_CONFIG=fireworks \
   pytest -s -v tests/integration/agents/test_agents.py \
  --safety-shield meta-llama/Llama-Guard-3-8B --text-model meta-llama/Llama-3.1-8B-Instruct
```

docs/source/building_applications/agent.md

@@ -14,18 +14,16 @@ Agents are configured using the `AgentConfig` class, which includes:
 - **Safety Shields**: Guardrails to ensure responsible AI behavior
 
 ```python
-from llama_stack_client.types.agent_create_params import AgentConfig
 from llama_stack_client.lib.agents.agent import Agent
 
-# Configure an agent
-agent_config = AgentConfig(
-    model="meta-llama/Llama-3-70b-chat",
-    instructions="You are a helpful assistant that can use tools to answer questions.",
-    toolgroups=["builtin::code_interpreter", "builtin::rag/knowledge_search"],
-)
 
 # Create the agent
-agent = Agent(llama_stack_client, agent_config)
+agent = Agent(
+    llama_stack_client,
+    model="meta-llama/Llama-3-70b-chat",
+    instructions="You are a helpful assistant that can use tools to answer questions.",
+    tools=["builtin::code_interpreter", "builtin::rag/knowledge_search"],
+)
 ```
 
 ### 2. Sessions

docs/source/building_applications/agent_execution_loop.md

@@ -70,18 +70,18 @@ Each step in this process can be monitored and controlled through configurations
 from llama_stack_client import LlamaStackClient
 from llama_stack_client.lib.agents.agent import Agent
 from llama_stack_client.lib.agents.event_logger import EventLogger
-from llama_stack_client.types.agent_create_params import AgentConfig
 from rich.pretty import pprint
 
 # Replace host and port
 client = LlamaStackClient(base_url=f"http://{HOST}:{PORT}")
 
-agent_config = AgentConfig(
+agent = Agent(
+    client,
     # Check with `llama-stack-client models list`
     model="Llama3.2-3B-Instruct",
     instructions="You are a helpful assistant",
     # Enable both RAG and tool usage
-    toolgroups=[
+    tools=[
         {
             "name": "builtin::rag/knowledge_search",
             "args": {"vector_db_ids": ["my_docs"]},
@@ -98,8 +98,6 @@ agent_config = AgentConfig(
         "max_tokens": 2048,
     },
 )
-
-agent = Agent(client, agent_config)
 session_id = agent.create_session("monitored_session")
 
 # Stream the agent's execution steps

docs/source/building_applications/evals.md

@@ -25,17 +25,13 @@ In this example, we will show you how to:
 ```python
 from llama_stack_client.lib.agents.agent import Agent
 from llama_stack_client.lib.agents.event_logger import EventLogger
-from llama_stack_client.types.agent_create_params import AgentConfig
 
-agent_config = AgentConfig(
+agent = Agent(
+    client,
     model="meta-llama/Llama-3.3-70B-Instruct",
     instructions="You are a helpful assistant. Use search tool to answer the questions. ",
-    toolgroups=["builtin::websearch"],
-    input_shields=[],
-    output_shields=[],
-    enable_session_persistence=False,
+    tools=["builtin::websearch"],
 )
-agent = Agent(client, agent_config)
 user_prompts = [
     "Which teams played in the NBA western conference finals of 2024. Search the web for the answer.",
     "In which episode and season of South Park does Bill Cosby (BSM-471) first appear? Give me the number and title. Search the web for the answer.",

docs/source/building_applications/rag.md

@@ -86,15 +86,14 @@ results = client.tool_runtime.rag_tool.query(
 One of the most powerful patterns is combining agents with RAG capabilities. Here's a complete example:
 
 ```python
-from llama_stack_client.types.agent_create_params import AgentConfig
 from llama_stack_client.lib.agents.agent import Agent
 
-# Configure agent with memory
-agent_config = AgentConfig(
+# Create agent with memory
+agent = Agent(
+    client,
     model="meta-llama/Llama-3.3-70B-Instruct",
     instructions="You are a helpful assistant",
-    enable_session_persistence=False,
-    toolgroups=[
+    tools=[
         {
             "name": "builtin::rag/knowledge_search",
             "args": {
@@ -103,8 +102,6 @@ agent_config = AgentConfig(
         }
     ],
 )
-
-agent = Agent(client, agent_config)
 session_id = agent.create_session("rag_session")
 
 

docs/source/building_applications/tools.md

@@ -149,15 +149,7 @@ def my_tool(input: int) -> int:
 Once defined, simply pass the tool to the agent config. `Agent` will take care of the rest (calling the model with the tool definition, executing the tool, and returning the result to the model for the next iteration).
 ```python
 # Example agent config with client provided tools
-client_tools = [
-    my_tool,
-]
-
-agent_config = AgentConfig(
-    ...,
-    client_tools=[client_tool.get_tool_definition() for client_tool in client_tools],
-)
-agent = Agent(client, agent_config, client_tools)
+agent = Agent(client, ..., tools=[my_tool])
 ```
 
 Refer to [llama-stack-apps](https://github.com/meta-llama/llama-stack-apps/blob/main/examples/agents/e2e_loop_with_client_tools.py) for an example of how to use client provided tools.
@@ -194,10 +186,10 @@ group_tools = client.tools.list_tools(toolgroup_id="search_tools")
 
 ```python
 from llama_stack_client.lib.agents.agent import Agent
-from llama_stack_client.types.agent_create_params import AgentConfig
 
-# Configure the AI agent with necessary parameters
-agent_config = AgentConfig(
+# Instantiate the AI agent with the given configuration
+agent = Agent(
+    client,
     name="code-interpreter",
     description="A code interpreter agent for executing Python code snippets",
     instructions="""
@@ -205,14 +197,10 @@ agent_config = AgentConfig(
     Always show the generated code, never generate your own code, and never anticipate results.
     """,
     model="meta-llama/Llama-3.2-3B-Instruct",
-    toolgroups=["builtin::code_interpreter"],
+    tools=["builtin::code_interpreter"],
     max_infer_iters=5,
-    enable_session_persistence=False,
 )
 
-# Instantiate the AI agent with the given configuration
-agent = Agent(client, agent_config)
-
 # Start a session
 session_id = agent.create_session("tool_session")
 

docs/source/getting_started/index.md

@@ -184,7 +184,6 @@ from termcolor import cprint
 
 from llama_stack_client.lib.agents.agent import Agent
 from llama_stack_client.lib.agents.event_logger import EventLogger
-from llama_stack_client.types.agent_create_params import AgentConfig
 from llama_stack_client.types import Document
 
 
@@ -241,13 +240,14 @@ client.tool_runtime.rag_tool.insert(
     chunk_size_in_tokens=512,
 )
 
-agent_config = AgentConfig(
+rag_agent = Agent(
+    client,
     model=os.environ["INFERENCE_MODEL"],
     # Define instructions for the agent ( aka system prompt)
     instructions="You are a helpful assistant",
     enable_session_persistence=False,
     # Define tools available to the agent
-    toolgroups=[
+    tools=[
         {
             "name": "builtin::rag/knowledge_search",
             "args": {
@@ -256,8 +256,6 @@ agent_config = AgentConfig(
         }
     ],
 )
-
-rag_agent = Agent(client, agent_config)
 session_id = rag_agent.create_session("test-session")
 
 user_prompts = [