Files
Evan Mattson f3db60fa65 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.
2026-05-04 21:21:40 +00:00

74 lines
2.2 KiB
Python

# Copyright (c) Microsoft. All rights reserved.
import asyncio
from typing import Literal
from agent_framework import Agent
from agent_framework.openai import OpenAIChatClient, OpenAIChatOptions
from dotenv import load_dotenv
Verbosity = Literal["low", "medium", "high"]
load_dotenv()
"""
OpenAI Chat Client Verbosity Example
Demonstrates the GPT-5 ``verbosity`` parameter on the Responses API. ``verbosity``
controls how concise or detailed the model's natural-language output is and accepts
``"low"``, ``"medium"``, or ``"high"``.
The framework exposes ``verbosity`` as a top-level option on ``OpenAIChatOptions``
(parallel to ``reasoning``) and translates it to ``text.verbosity`` when calling the
Responses API.
"""
PROMPT = "Explain in your own words what photosynthesis is and why it matters."
async def run_with_verbosity(level: Verbosity) -> None:
"""Run the same prompt with a different verbosity setting and print the output length."""
agent = Agent(
client=OpenAIChatClient[OpenAIChatOptions](model="gpt-5"),
name=f"Explainer-{level}",
instructions="You are a friendly science explainer.",
default_options={"verbosity": level},
)
print(f"\033[92m=== verbosity={level!r} ===\033[0m")
response = await agent.run(PROMPT)
text = response.text or ""
print(text)
print(f"\n[chars: {len(text)}]\n")
async def run_per_call_override() -> None:
"""Show that verbosity can be overridden per ``run`` call."""
agent = Agent(
client=OpenAIChatClient[OpenAIChatOptions](model="gpt-5"),
name="Explainer-default",
instructions="You are a friendly science explainer.",
default_options={"verbosity": "high"},
)
print("\033[92m=== per-call override: verbosity='low' ===\033[0m")
response = await agent.run(PROMPT, options={"verbosity": "low"})
text = response.text or ""
print(text)
print(f"\n[chars: {len(text)}]\n")
async def main() -> None:
print("\033[92m=== OpenAI Chat Client Verbosity Example ===\033[0m\n")
levels: tuple[Verbosity, ...] = ("low", "medium", "high")
for level in levels:
await run_with_verbosity(level)
await run_per_call_override()
if __name__ == "__main__":
asyncio.run(main())