Python: Support GPT-5 verbosity option and restore Foundry agent_reference (#5619)

* Python: Support GPT-5 verbosity option and restore Foundry agent_reference

Adds verbosity as a typed Literal["low","medium","high"] field on
OpenAIChatOptions (Responses API) and OpenAIChatCompletionOptions (Chat
Completions API), set in the same way as the existing reasoning options.
For the Responses API, top-level verbosity is translated to the nested
text.verbosity shape the OpenAI service expects. The same field flows
through to FoundryChatClient via the existing FoundryChatOptions alias.

Also fixes #5582: PR #5447 removed the agent_reference injection from
RawFoundryAgentChatClient._prepare_options, so first-turn calls against
a Foundry Prompt Agent went out without model and without agent_reference
and were rejected by the Responses API with "Missing required parameter:
'model'". Restores the injection on the non-preview path
(allow_preview=False) and adds a guard test that asserts the preview
path does not inject agent_reference, since the preview SDK injects it
via project_client.get_openai_client(agent_name=...).

Closes #5516
Closes #5582

* Python: Address Copilot review on PR #5619

- Foundry verbosity sample docstring: replace the misleading "set deployment
  name on model=" instruction with the actual env-var pattern the sample relies
  on (FOUNDRY_PROJECT_ENDPOINT and FOUNDRY_MODEL).
- _build_agent_reference docstring: clarify the helper is used for both
  Prompt Agents and HostedAgents on the non-preview path.
- Add a Responses API test that locks in the documented precedence rule:
  when both top-level verbosity and text["verbosity"] are supplied, the
  top-level value wins.

* Python: Drop redundant Foundry verbosity sample and list OpenAI sample in README

- Remove samples/02-agents/providers/foundry/foundry_chat_client_verbosity.py
  per review feedback. The verbosity functionality is identical across the
  OpenAI and Foundry clients (FoundryChatOptions is an alias of
  OpenAIChatOptions), so a single sample on the OpenAI side is sufficient.
- Add the new client_verbosity.py entry to the OpenAI samples README.

python/packages/openai/tests/openai/test_openai_chat_client.py

@@ -343,6 +343,76 @@ async def test_get_response_with_all_parameters() -> None:
     assert run_options["input"][1]["content"][0]["text"] == "Test message"
 
 
+def test_openai_chat_options_declares_verbosity_field() -> None:
+    """OpenAIChatOptions declares verbosity as a typed Literal field."""
+    from typing import get_args, get_type_hints
+
+    from agent_framework_openai import OpenAIChatOptions
+
+    annotations = get_type_hints(OpenAIChatOptions)
+    assert "verbosity" in annotations
+    assert {"low", "medium", "high"} <= set(get_args(annotations["verbosity"]))
+
+
+async def test_verbosity_option_translates_to_text_field() -> None:
+    """Top-level verbosity is translated to text.verbosity for the Responses API."""
+    client = OpenAIChatClient(model="test-model", api_key="test-key")
+    _, run_options, _ = await client._prepare_request(
+        messages=[Message(role="user", contents=["Test message"])],
+        options={"verbosity": "low"},
+    )
+
+    assert "verbosity" not in run_options
+    assert run_options["text"] == {"verbosity": "low"}
+
+
+async def test_verbosity_option_merges_with_response_format() -> None:
+    """Verbosity merges into text config alongside response_format-derived format."""
+    client = OpenAIChatClient(model="test-model", api_key="test-key")
+    _, run_options, _ = await client._prepare_request(
+        messages=[Message(role="user", contents=["Test message"])],
+        options={
+            "verbosity": "high",
+            "response_format": OutputStruct,
+        },
+    )
+
+    assert "verbosity" not in run_options
+    assert run_options["text"]["verbosity"] == "high"
+    assert run_options["text_format"] is OutputStruct
+
+
+async def test_verbosity_option_top_level_overrides_nested_text_verbosity() -> None:
+    """When both top-level and text['verbosity'] are set, the top-level value wins."""
+    client = OpenAIChatClient(model="test-model", api_key="test-key")
+    _, run_options, _ = await client._prepare_request(
+        messages=[Message(role="user", contents=["Test message"])],
+        options={
+            "verbosity": "high",
+            "text": {"verbosity": "low"},
+        },
+    )
+
+    assert "verbosity" not in run_options
+    assert run_options["text"]["verbosity"] == "high"
+
+
+async def test_verbosity_option_merges_with_explicit_text_config() -> None:
+    """Verbosity merges into a user-provided text config without overwriting other keys."""
+    client = OpenAIChatClient(model="test-model", api_key="test-key")
+    _, run_options, _ = await client._prepare_request(
+        messages=[Message(role="user", contents=["Test message"])],
+        options={
+            "verbosity": "medium",
+            "text": {"format": {"type": "text"}},
+        },
+    )
+
+    assert "verbosity" not in run_options
+    assert run_options["text"]["verbosity"] == "medium"
+    assert run_options["text"]["format"] == {"type": "text"}
+
+
 @pytest.mark.asyncio
 async def test_web_search_tool_with_location() -> None:
     """Test web search tool with location parameters."""

python/packages/openai/tests/openai/test_openai_chat_completion_client.py

@@ -1563,6 +1563,27 @@ def test_prepare_options_removes_parallel_tool_calls_when_no_tools(
     assert "parallel_tool_calls" not in prepared_options
 
 
+def test_openai_chat_completion_options_declares_verbosity_field() -> None:
+    """OpenAIChatCompletionOptions declares verbosity as a typed Literal field."""
+    from typing import get_args, get_type_hints
+
+    from agent_framework_openai import OpenAIChatCompletionOptions
+
+    annotations = get_type_hints(OpenAIChatCompletionOptions)
+    assert "verbosity" in annotations
+    assert {"low", "medium", "high"} <= set(get_args(annotations["verbosity"]))
+
+
+def test_prepare_options_forwards_verbosity(openai_unit_test_env: dict[str, str]) -> None:
+    """Verbosity passes through unchanged for the Chat Completions API."""
+    client = OpenAIChatCompletionClient()
+
+    messages = [Message(role="user", contents=["test"])]
+    prepared_options = client._prepare_options(messages, {"verbosity": "low"})
+
+    assert prepared_options["verbosity"] == "low"
+
+
 def test_prepare_options_excludes_conversation_id(openai_unit_test_env: dict[str, str]) -> None:
     """Test that conversation_id is excluded from prepared options for chat completions."""
     client = OpenAIChatCompletionClient()