Fix eval samples: add required client= argument to Agent()

The upstream provider-leading client refactor (#4818) made client=
a required parameter on Agent(). Update the three getting-started
eval samples to use OpenAIResponsesClient(), matching the pattern
used by all other 02-agents and 03-workflows samples.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: alliscode

python/samples/02-agents/evaluation/evaluate_agent.py

@@ -20,6 +20,7 @@
     evaluator,
     keyword_check,
 )
+from agent_framework.openai import OpenAIResponsesClient
 
 
 # A custom check — parameter names determine what data you receive
@@ -32,7 +33,8 @@ def is_helpful(response: str) -> bool:
 
 async def main() -> None:
     agent = Agent(
-        model="gpt-4o-mini",
+        client=OpenAIResponsesClient(),
+        name="weather-assistant",
         instructions="You are a helpful weather assistant.",
     )
 

python/samples/02-agents/evaluation/evaluate_with_expected.py

@@ -20,6 +20,7 @@
     evaluator,
     tool_calls_present,
 )
+from agent_framework.openai import OpenAIResponsesClient
 
 
 @evaluator
@@ -34,7 +35,8 @@ def response_matches_expected(response: str, expected_output: str) -> float:
 
 async def main() -> None:
     agent = Agent(
-        model="gpt-4o-mini",
+        client=OpenAIResponsesClient(),
+        name="math-tutor",
         instructions="You are a math tutor. Answer concisely.",
     )
 

python/samples/03-workflows/evaluation/evaluate_workflow.py

@@ -21,6 +21,7 @@
     evaluator,
     keyword_check,
 )
+from agent_framework.openai import OpenAIResponsesClient
 
 
 @evaluator
@@ -31,8 +32,11 @@ def is_nonempty(response: str) -> bool:
 
 async def main() -> None:
     # Build a simple planner → executor workflow
-    planner = Agent(model="gpt-4o-mini", instructions="You plan trips. Output a bullet-point plan.")
-    executor_agent = Agent(model="gpt-4o-mini", instructions="You execute travel plans. Book the items listed.")
+    client = OpenAIResponsesClient()
+    planner = Agent(client=client, name="planner", instructions="You plan trips. Output a bullet-point plan.")
+    executor_agent = Agent(
+        client=client, name="executor", instructions="You execute travel plans. Book the items listed."
+    )
 
     workflow = WorkflowBuilder(start_executor=planner).add_edge(planner, executor_agent).build()