Python: [BREAKING] Python: Provider-leading client design & OpenAI package extraction (#4818)

* Python: Provider-leading client design & OpenAI package extraction

Major refactoring of the Python Agent Framework client architecture:

- Extract OpenAI clients into new `agent-framework-openai` package
- Core package no longer depends on openai, azure-identity, azure-ai-projects
- Rename clients for discoverability: OpenAIResponsesClient → OpenAIChatClient,
  OpenAIChatClient → OpenAIChatCompletionClient
- Unify `model_id`/`deployment_name`/`model_deployment_name` → `model` param
- New FoundryChatClient for Azure AI Foundry Responses API
- New FoundryAgent/FoundryAgentClient for connecting to pre-configured Foundry agents
- Remove OpenAIBase/OpenAIConfigMixin from non-deprecated client MRO
- Deprecate AzureOpenAI* clients, AzureAIClient, OpenAIAssistantsClient
- Reorganize samples: azure_openai+azure_ai+azure_ai_agent → azure/
- ADR-0020: Provider-Leading Client Design

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

* fix: missing Agent imports in samples, .model_id → .model in foundry_local sample

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

* fix: CI failures — mypy errors, coverage targets, sample imports

- azure-ai mypy: add type ignores for TypedDict total=, model arg, forward ref
- Coverage: replace core.azure/openai targets with openai package target
- project_provider: add type annotation for opts dict

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

* fix: populate openai .pyi stub, fix broken README links, coverage targets

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

* fixes

* updated observabilitty

* reset azure init.pyi

* fix errors

* updated adr number

* fix foundry local

* fixed not renamed docstrings and comments, and added deprecated markers to old classes

* fix tests and pyprojects

* fix test vars

* updated function tests

* update durable

* updated test setup for functions

* Fix Foundry auth in workflow samples

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

* Stabilize Python integration workflows

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

* Update hosting samples for Foundry

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

* Trigger full CI rerun

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

* Trigger CI rerun again

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

* trigger rerun

* trigger rerun

* fix for litellm

* undo durabletask changes

* Move Foundry APIs into foundry namespace

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

* Fix Foundry pyproject formatting

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

* Split provider samples by Foundry surface

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

* Restore hosting sample requirements

Also fix the Foundry Local sample link after the provider sample move.

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

* updated tests

* udpated foundry integration tests

* removed dist from azurefunctions tests

* Use separate Foundry clients for concurrent agents

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

* fix client setup in azfunc and durable

* disabled two tests

* updated setup for some function and durable tests

* improved azure openai setup with new clients

* ignore deprecated

* fixes

* skip 11

* remove openai assistants int tests

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
Eduard van Valkenburg
2026-03-25 10:56:29 +01:00
committed by GitHub
Unverified
parent 4b533608b6
commit 5e056b672e
485 changed files with 9784 additions and 12084 deletions
@@ -44,7 +44,7 @@ async def non_streaming_example() -> None:
# Create a new assistant via the provider
agent = await provider.create_agent(
name="WeatherAssistant",
model=os.environ.get("OPENAI_CHAT_MODEL_ID", "gpt-4"),
model=os.environ.get("OPENAI_MODEL", "gpt-4"),
instructions="You are a helpful weather agent.",
tools=[get_weather],
)
@@ -69,7 +69,7 @@ async def streaming_example() -> None:
# Create a new assistant via the provider
agent = await provider.create_agent(
name="WeatherAssistant",
model=os.environ.get("OPENAI_CHAT_MODEL_ID", "gpt-4"),
model=os.environ.get("OPENAI_MODEL", "gpt-4"),
instructions="You are a helpful weather agent.",
tools=[get_weather],
)
@@ -5,7 +5,7 @@ import os
from random import randint
from typing import Annotated
from agent_framework import tool
from agent_framework import Agent, tool
from agent_framework.openai import OpenAIAssistantProvider
from dotenv import load_dotenv
from openai import AsyncOpenAI
@@ -46,7 +46,7 @@ async def create_agent_example() -> None:
):
agent = await provider.create_agent(
name="WeatherAssistant",
model=os.environ.get("OPENAI_CHAT_MODEL_ID", "gpt-4"),
model=os.environ.get("OPENAI_MODEL", "gpt-4"),
instructions="You are a helpful weather assistant.",
tools=[get_weather],
)
@@ -69,7 +69,7 @@ async def get_agent_example() -> None:
):
# Create an assistant directly with SDK (simulating pre-existing assistant)
sdk_assistant = await client.beta.assistants.create(
model=os.environ.get("OPENAI_CHAT_MODEL_ID", "gpt-4"),
model=os.environ.get("OPENAI_MODEL", "gpt-4"),
name="ExistingAssistant",
instructions="You always respond with 'Hello!'",
)
@@ -86,7 +86,7 @@ async def get_agent_example() -> None:
async def as_agent_example() -> None:
"""Wrap an SDK Assistant object using provider.as_agent()."""
"""Wrap an SDK Assistant object using Agent(client=provider, ...)."""
print("\n--- as_agent() ---")
async with (
@@ -95,14 +95,14 @@ async def as_agent_example() -> None:
):
# Create assistant using SDK
sdk_assistant = await client.beta.assistants.create(
model=os.environ.get("OPENAI_CHAT_MODEL_ID", "gpt-4"),
model=os.environ.get("OPENAI_MODEL", "gpt-4"),
name="WrappedAssistant",
instructions="You respond with poetry.",
)
try:
# Wrap synchronously (no HTTP call)
agent = provider.as_agent(sdk_assistant)
agent = Agent(client=provider, agent=sdk_assistant)
print(f"Wrapped: {agent.name} (ID: {agent.id})")
result = await agent.run("Tell me about the sunset.")
@@ -121,14 +121,14 @@ async def multiple_agents_example() -> None:
):
weather_agent = await provider.create_agent(
name="WeatherSpecialist",
model=os.environ.get("OPENAI_CHAT_MODEL_ID", "gpt-4"),
model=os.environ.get("OPENAI_MODEL", "gpt-4"),
instructions="You are a weather specialist.",
tools=[get_weather],
)
greeter_agent = await provider.create_agent(
name="GreeterAgent",
model=os.environ.get("OPENAI_CHAT_MODEL_ID", "gpt-4"),
model=os.environ.get("OPENAI_MODEL", "gpt-4"),
instructions="You are a friendly greeter.",
)
@@ -55,7 +55,7 @@ async def main() -> None:
agent = await provider.create_agent(
name="CodeHelper",
model=os.environ.get("OPENAI_CHAT_MODEL_ID", "gpt-4"),
model=os.environ.get("OPENAI_MODEL", "gpt-4"),
instructions="You are a helpful assistant that can write and execute Python code to solve problems.",
tools=[chat_client.get_code_interpreter_tool()],
)
@@ -5,7 +5,7 @@ import os
from random import randint
from typing import Annotated
from agent_framework import tool
from agent_framework import Agent, tool
from agent_framework.openai import OpenAIAssistantProvider
from dotenv import load_dotenv
from openai import AsyncOpenAI
@@ -43,7 +43,7 @@ async def example_get_agent_by_id() -> None:
# Create an assistant via SDK (simulating an existing assistant)
created_assistant = await client.beta.assistants.create(
model=os.environ.get("OPENAI_CHAT_MODEL_ID", "gpt-4"),
model=os.environ.get("OPENAI_MODEL", "gpt-4"),
name="WeatherAssistant",
tools=[
{
@@ -86,7 +86,7 @@ async def example_as_agent_wrap_sdk_object() -> None:
# Create and fetch an assistant via SDK
created_assistant = await client.beta.assistants.create(
model=os.environ.get("OPENAI_CHAT_MODEL_ID", "gpt-4"),
model=os.environ.get("OPENAI_MODEL", "gpt-4"),
name="SimpleAssistant",
instructions="You are a friendly assistant.",
)
@@ -94,8 +94,9 @@ async def example_as_agent_wrap_sdk_object() -> None:
try:
# Use as_agent() to wrap the SDK object
agent = provider.as_agent(
created_assistant,
agent = Agent(
client=provider,
agent=created_assistant,
instructions="You are an extremely helpful assistant. Be enthusiastic!",
)
@@ -43,7 +43,7 @@ async def main() -> None:
agent = await provider.create_agent(
name="WeatherAssistant",
model=os.environ["OPENAI_CHAT_MODEL_ID"],
model=os.environ["OPENAI_MODEL"],
instructions="You are a helpful weather agent.",
tools=[get_weather],
)
@@ -50,7 +50,7 @@ async def main() -> None:
agent = await provider.create_agent(
name="SearchAssistant",
model=os.environ.get("OPENAI_CHAT_MODEL_ID", "gpt-4"),
model=os.environ.get("OPENAI_MODEL", "gpt-4"),
instructions="You are a helpful assistant that searches files in a knowledge base.",
tools=[chat_client.get_file_search_tool()],
)
@@ -53,7 +53,7 @@ async def tools_on_agent_level() -> None:
# The agent can use these tools for any query during its lifetime
agent = await provider.create_agent(
name="InfoAssistant",
model=os.environ.get("OPENAI_CHAT_MODEL_ID", "gpt-4"),
model=os.environ.get("OPENAI_MODEL", "gpt-4"),
instructions="You are a helpful assistant that can provide weather and time information.",
tools=[get_weather, get_time], # Tools defined at agent creation
)
@@ -90,7 +90,7 @@ async def tools_on_run_level() -> None:
# Agent created with base tools, additional tools can be passed at run time
agent = await provider.create_agent(
name="FlexibleAssistant",
model=os.environ.get("OPENAI_CHAT_MODEL_ID", "gpt-4"),
model=os.environ.get("OPENAI_MODEL", "gpt-4"),
instructions="You are a helpful assistant.",
tools=[get_weather], # Base tool
)
@@ -127,7 +127,7 @@ async def mixed_tools_example() -> None:
# Agent created with some base tools
agent = await provider.create_agent(
name="ComprehensiveAssistant",
model=os.environ.get("OPENAI_CHAT_MODEL_ID", "gpt-4"),
model=os.environ.get("OPENAI_MODEL", "gpt-4"),
instructions="You are a comprehensive assistant that can help with various information requests.",
tools=[get_weather], # Base tool available for all queries
)
@@ -50,7 +50,7 @@ async def main() -> None:
# Create agent with default response_format (WeatherInfo)
agent = await provider.create_agent(
name="StructuredReporter",
model=os.environ.get("OPENAI_CHAT_MODEL_ID", "gpt-4"),
model=os.environ.get("OPENAI_MODEL", "gpt-4"),
instructions="Return structured JSON based on the requested format.",
default_options={"response_format": WeatherInfo},
)
@@ -43,7 +43,7 @@ async def example_with_automatic_session_creation() -> None:
agent = await provider.create_agent(
name="WeatherAssistant",
model=os.environ.get("OPENAI_CHAT_MODEL_ID", "gpt-4"),
model=os.environ.get("OPENAI_MODEL", "gpt-4"),
instructions="You are a helpful weather agent.",
tools=[get_weather],
)
@@ -75,7 +75,7 @@ async def example_with_session_persistence() -> None:
agent = await provider.create_agent(
name="WeatherAssistant",
model=os.environ.get("OPENAI_CHAT_MODEL_ID", "gpt-4"),
model=os.environ.get("OPENAI_MODEL", "gpt-4"),
instructions="You are a helpful weather agent.",
tools=[get_weather],
)
@@ -120,7 +120,7 @@ async def example_with_existing_session_id() -> None:
agent = await provider.create_agent(
name="WeatherAssistant",
model=os.environ.get("OPENAI_CHAT_MODEL_ID", "gpt-4"),
model=os.environ.get("OPENAI_MODEL", "gpt-4"),
instructions="You are a helpful weather agent.",
tools=[get_weather],
)
@@ -4,7 +4,7 @@ import asyncio
from random import randint
from typing import Annotated
from agent_framework import tool
from agent_framework import Agent, tool
from agent_framework.openai import OpenAIChatClient
from dotenv import load_dotenv
@@ -35,7 +35,8 @@ async def non_streaming_example() -> None:
"""Example of non-streaming response (get the complete result at once)."""
print("=== Non-streaming Response Example ===")
agent = OpenAIChatClient().as_agent(
agent = Agent(
client=OpenAIChatClient(),
name="WeatherAgent",
instructions="You are a helpful weather agent.",
tools=get_weather,
@@ -51,7 +52,8 @@ async def streaming_example() -> None:
"""Example of streaming response (get results as they are generated)."""
print("=== Streaming Response Example ===")
agent = OpenAIChatClient().as_agent(
agent = Agent(
client=OpenAIChatClient(),
name="WeatherAgent",
instructions="You are a helpful weather agent.",
tools=get_weather,
@@ -5,7 +5,7 @@ import os
from random import randint
from typing import Annotated
from agent_framework import tool
from agent_framework import Agent, tool
from agent_framework.openai import OpenAIChatClient
from dotenv import load_dotenv
from pydantic import Field
@@ -36,10 +36,13 @@ def get_weather(
async def main() -> None:
print("=== OpenAI Chat Client with Explicit Settings ===")
agent = OpenAIChatClient(
model_id=os.environ["OPENAI_CHAT_MODEL_ID"],
_client = OpenAIChatClient(
model=os.environ["OPENAI_MODEL"],
api_key=os.environ["OPENAI_API_KEY"],
).as_agent(
)
agent = Agent(
client=_client,
instructions="You are a helpful weather agent.",
tools=get_weather,
)
@@ -59,7 +59,8 @@ async def mcp_tools_on_agent_level() -> None:
# Tools are provided when creating the agent
# The agent can use these tools for any query during its lifetime
# The agent will connect to the MCP server through its context manager.
async with OpenAIChatClient().as_agent(
async with Agent(
client=OpenAIChatClient(),
name="DocsAgent",
instructions="You are a helpful assistant that can help with microsoft documentation questions.",
tools=MCPStreamableHTTPTool( # Tools defined at agent creation
@@ -3,6 +3,7 @@
import asyncio
import json
from agent_framework import Agent
from agent_framework.openai import OpenAIChatClient, OpenAIChatOptions
from dotenv import load_dotenv
@@ -36,7 +37,8 @@ runtime_schema = {
async def non_streaming_example() -> None:
print("=== Non-streaming runtime JSON schema example ===")
agent = OpenAIChatClient[OpenAIChatOptions]().as_agent(
agent = Agent(
client=OpenAIChatClient[OpenAIChatOptions](),
name="RuntimeSchemaAgent",
instructions="Return only JSON that matches the provided schema. Do not add commentary.",
)
@@ -69,7 +71,8 @@ async def non_streaming_example() -> None:
async def streaming_example() -> None:
print("=== Streaming runtime JSON schema example ===")
agent = OpenAIChatClient().as_agent(
agent = Agent(
client=OpenAIChatClient(),
name="RuntimeSchemaAgent",
instructions="Return only JSON that matches the provided schema. Do not add commentary.",
)
@@ -18,7 +18,7 @@ for real-time information retrieval and current data access.
async def main() -> None:
client = OpenAIChatClient(model_id="gpt-4o-search-preview")
client = OpenAIChatClient(model="gpt-4o-search-preview")
# Create web search tool with location context
web_search_tool = client.get_web_search_tool(
@@ -2,7 +2,7 @@
import asyncio
from agent_framework import Content
from agent_framework import Agent, Content
from agent_framework.openai import OpenAIResponsesClient
from dotenv import load_dotenv
@@ -21,7 +21,8 @@ async def main():
print("=== OpenAI Responses Agent with Image Analysis ===")
# 1. Create an OpenAI Responses agent with vision capabilities
agent = OpenAIResponsesClient().as_agent(
agent = Agent(
client=OpenAIResponsesClient(),
name="VisionAgent",
instructions="You are a image analysist, you get a image and need to respond with what you see in the picture.",
)
@@ -6,7 +6,7 @@ import tempfile
import urllib.request as urllib_request
from pathlib import Path
from agent_framework import Content
from agent_framework import Agent, Content
from agent_framework.openai import OpenAIResponsesClient
from dotenv import load_dotenv
@@ -61,7 +61,8 @@ async def main() -> None:
# Create an agent with customized image generation options
client = OpenAIResponsesClient()
agent = client.as_agent(
agent = Agent(
client=client,
instructions="You are a helpful AI that can generate images.",
tools=[
client.get_image_generation_tool(
@@ -2,6 +2,7 @@
import asyncio
from agent_framework import Agent
from agent_framework.openai import OpenAIResponsesClient, OpenAIResponsesOptions
from dotenv import load_dotenv
@@ -23,7 +24,8 @@ In this case they are here: https://platform.openai.com/docs/api-reference/respo
"""
agent = OpenAIResponsesClient[OpenAIResponsesOptions](model_id="gpt-5").as_agent(
agent = Agent(
client=OpenAIResponsesClient[OpenAIResponsesOptions](model_id="gpt-5"),
name="MathHelper",
instructions="You are a personal math tutor. When asked a math question, "
"reason over how best to approach the problem and share your thought process.",
@@ -6,23 +6,19 @@ import tempfile
from pathlib import Path
import anyio
from agent_framework import Content
from agent_framework import Agent, Content
from agent_framework.openai import OpenAIResponsesClient
from dotenv import load_dotenv
# Load environment variables from .env file
load_dotenv()
"""OpenAI Responses Client Streaming Image Generation Example
Demonstrates streaming partial image generation using OpenAI's image generation tool.
Shows progressive image rendering with partial images for improved user experience.
Note: The number of partial images received depends on generation speed:
- High quality/complex images: More partials (generation takes longer)
- Low quality/simple images: Fewer partials (generation completes quickly)
- You may receive fewer partial images than requested if generation is fast
Important: The final partial image IS the complete, full-quality image. Each partial
represents a progressive refinement, with the last one being the finished result.
"""
@@ -35,7 +31,6 @@ async def save_image_from_data_uri(data_uri: str, filename: str) -> None:
# Extract base64 data
base64_data = data_uri.split(",", 1)[1]
image_bytes = base64.b64decode(base64_data)
# Save to file
await anyio.Path(filename).write_bytes(image_bytes)
print(f" Saved: {filename} ({len(image_bytes) / 1024:.1f} KB)")
@@ -46,10 +41,10 @@ async def save_image_from_data_uri(data_uri: str, filename: str) -> None:
async def main():
"""Demonstrate streaming image generation with partial images."""
print("=== OpenAI Streaming Image Generation Example ===\n")
# Create agent with streaming image generation enabled
client = OpenAIResponsesClient()
agent = client.as_agent(
agent = Agent(
client=client,
instructions="You are a helpful agent that can generate images.",
tools=[
client.get_image_generation_tool(
@@ -59,18 +54,14 @@ async def main():
)
],
)
query = "Draw a beautiful sunset over a calm ocean with sailboats"
print(f" User: {query}")
print()
# Track partial images
image_count = 0
# Use temp directory for output
output_dir = Path(tempfile.gettempdir()) / "generated_images"
output_dir.mkdir(exist_ok=True)
print(" Streaming response:")
async for update in agent.run(query, stream=True):
for content in update.contents:
@@ -81,18 +72,14 @@ async def main():
image_output: Content = content.outputs
if image_output.type == "data" and image_output.additional_properties.get("is_partial_image"):
print(f" Image {image_count} received")
# Extract file extension from media_type (e.g., "image/png" -> "png")
extension = "png" # Default fallback
if image_output.media_type and "/" in image_output.media_type:
extension = image_output.media_type.split("/")[-1]
# Save images with correct extension
filename = output_dir / f"image{image_count}.{extension}"
await save_image_from_data_uri(image_output.uri, str(filename))
image_count += 1
# Summary
print("\n Summary:")
print(f" Images received: {image_count}")
@@ -3,7 +3,7 @@
import asyncio
from collections.abc import Awaitable, Callable
from agent_framework import FunctionInvocationContext
from agent_framework import Agent, FunctionInvocationContext
from agent_framework.openai import OpenAIResponsesClient
from dotenv import load_dotenv
@@ -40,7 +40,8 @@ async def main() -> None:
client = OpenAIResponsesClient()
# Create a specialized writer agent
writer = client.as_agent(
writer = Agent(
client=client,
name="WriterAgent",
instructions="You are a creative writer. Write short, engaging content.",
)
@@ -54,7 +55,8 @@ async def main() -> None:
)
# Create coordinator agent with writer as a tool
coordinator = client.as_agent(
coordinator = Agent(
client=client,
name="CoordinatorAgent",
instructions="You coordinate with specialized agents. Delegate writing tasks to the creative_writer tool.",
tools=[writer_tool],
@@ -5,7 +5,7 @@ import os
from random import randint
from typing import Annotated
from agent_framework import tool
from agent_framework import Agent, tool
from agent_framework.openai import OpenAIResponsesClient
from dotenv import load_dotenv
from pydantic import Field
@@ -36,10 +36,13 @@ def get_weather(
async def main() -> None:
print("=== OpenAI Responses Client with Explicit Settings ===")
agent = OpenAIResponsesClient(
model_id=os.environ["OPENAI_RESPONSES_MODEL_ID"],
_client = OpenAIResponsesClient(
model=os.environ["OPENAI_MODEL"],
api_key=os.environ["OPENAI_API_KEY"],
).as_agent(
)
agent = Agent(
client=_client,
instructions="You are a helpful weather agent.",
tools=get_weather,
)
@@ -3,6 +3,7 @@
import asyncio
import json
from agent_framework import Agent
from agent_framework.openai import OpenAIResponsesClient
from dotenv import load_dotenv
@@ -36,7 +37,8 @@ runtime_schema = {
async def non_streaming_example() -> None:
print("=== Non-streaming runtime JSON schema example ===")
agent = OpenAIResponsesClient().as_agent(
agent = Agent(
client=OpenAIResponsesClient(),
name="RuntimeSchemaAgent",
instructions="Return only JSON that matches the provided schema. Do not add commentary.",
)
@@ -69,7 +71,8 @@ async def non_streaming_example() -> None:
async def streaming_example() -> None:
print("=== Streaming runtime JSON schema example ===")
agent = OpenAIResponsesClient().as_agent(
agent = Agent(
client=OpenAIResponsesClient(),
name="RuntimeSchemaAgent",
instructions="Return only JSON that matches the provided schema. Do not add commentary.",
)
@@ -2,7 +2,7 @@
import asyncio
from agent_framework import AgentResponse
from agent_framework import Agent, AgentResponse
from agent_framework.openai import OpenAIResponsesClient
from dotenv import load_dotenv
from pydantic import BaseModel
@@ -29,7 +29,8 @@ async def non_streaming_example() -> None:
print("=== Non-streaming example ===")
# Create an OpenAI Responses agent
agent = OpenAIResponsesClient().as_agent(
agent = Agent(
client=OpenAIResponsesClient(),
name="CityAgent",
instructions="You are a helpful agent that describes cities in a structured format.",
)
@@ -54,7 +55,8 @@ async def streaming_example() -> None:
print("=== Streaming example ===")
# Create an OpenAI Responses agent
agent = OpenAIResponsesClient().as_agent(
agent = Agent(
client=OpenAIResponsesClient(),
name="CityAgent",
instructions="You are a helpful agent that describes cities in a structured format.",
)