agent/agent-framework
1
0
Fork 0
mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
* 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
Download Patch File Download Diff File Expand all files Collapse all files
python/samples/01-get-started/01_hello_agent.py
+9 -17
View File
@@ -1,39 +1,31 @@
# Copyright (c) Microsoft. All rights reserved.
import asyncio
import os
from agent_framework.azure import AzureOpenAIResponsesClient
from agent_framework import Agent
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
# Load environment variables from .env file
load_dotenv()
"""
Hello Agent — Simplest possible agent
This sample creates a minimal agent using AzureOpenAIResponsesClient via an
This sample creates a minimal agent using FoundryChatClient via an
Azure AI Foundry project endpoint, and runs it in both non-streaming and streaming modes.
There are XML tags in all of the get started samples, those are used to display the same code in the docs repo.
Environment variables:
AZURE_AI_PROJECT_ENDPOINT — Your Azure AI Foundry project endpoint
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME — Model deployment name (e.g. gpt-4o)
"""
async def main() -> None:
# <create_agent>
credential = AzureCliCredential()
client = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"],
credential=credential,
client = FoundryChatClient(
project_endpoint="https://your-project.services.ai.azure.com",
model="gpt-4o",
credential=AzureCliCredential(),
)
agent = client.as_agent(
agent = Agent(
client=client,
name="HelloAgent",
instructions="You are a friendly assistant. Keep your answers brief.",
)
python/samples/01-get-started/02_add_tools.py
+11 -18
View File
@@ -1,28 +1,19 @@
# Copyright (c) Microsoft. All rights reserved.
import asyncio
import os
from random import randint
from typing import Annotated
from agent_framework import tool
from agent_framework.azure import AzureOpenAIResponsesClient
from agent_framework import Agent, tool
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
from pydantic import Field
# Load environment variables from .env file
load_dotenv()
"""
Add Tools — Give your agent a function tool
This sample shows how to define a function tool with the @tool decorator
and wire it into an agent so the model can call it.
Environment variables:
AZURE_AI_PROJECT_ENDPOINT — Your Azure AI Foundry project endpoint
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME — Model deployment name (e.g. gpt-4o)
"""
@@ -36,22 +27,24 @@ def get_weather(
"""Get the weather for a given location."""
conditions = ["sunny", "cloudy", "rainy", "stormy"]
return f"The weather in {location} is {conditions[randint(0, 3)]} with a high of {randint(10, 30)}°C."
# </define_tool>
async def main() -> None:
credential = AzureCliCredential()
client = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"],
credential=credential,
client = FoundryChatClient(
project_endpoint="https://your-project.services.ai.azure.com",
model="gpt-4o",
credential=AzureCliCredential(),
)
# <create_agent_with_tools>
agent = client.as_agent(
agent = Agent(
client=client,
name="WeatherAgent",
instructions="You are a helpful weather agent. Use the get_weather tool to answer questions.",
tools=get_weather,
tools=[get_weather],
)
# </create_agent_with_tools>
python/samples/01-get-started/03_multi_turn.py
+8 -16
View File
@@ -1,37 +1,29 @@
# Copyright (c) Microsoft. All rights reserved.
import asyncio
import os
from agent_framework.azure import AzureOpenAIResponsesClient
from agent_framework import Agent
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
# Load environment variables from .env file
load_dotenv()
"""
Multi-Turn Conversations — Use AgentSession to maintain context
This sample shows how to keep conversation history across multiple calls
by reusing the same session object.
Environment variables:
AZURE_AI_PROJECT_ENDPOINT — Your Azure AI Foundry project endpoint
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME — Model deployment name (e.g. gpt-4o)
"""
async def main() -> None:
# <create_agent>
credential = AzureCliCredential()
client = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"],
credential=credential,
client = FoundryChatClient(
project_endpoint="https://your-project.services.ai.azure.com",
model="gpt-4o",
credential=AzureCliCredential(),
)
agent = client.as_agent(
agent = Agent(
client=client,
name="ConversationAgent",
instructions="You are a friendly assistant. Keep your answers brief.",
)
python/samples/01-get-started/04_memory.py
+10 -17
View File
@@ -1,16 +1,11 @@
# Copyright (c) Microsoft. All rights reserved.
import asyncio
import os
from typing import Any
from agent_framework import AgentSession, BaseContextProvider, SessionContext
from agent_framework.azure import AzureOpenAIResponsesClient
from agent_framework import Agent, AgentSession, BaseContextProvider, SessionContext
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
# Load environment variables from .env file
load_dotenv()
"""
Agent Memory with Context Providers and Session State
@@ -18,10 +13,6 @@ Agent Memory with Context Providers and Session State
Context providers inject dynamic context into each agent call. This sample
shows a provider that stores the user's name in session state and personalizes
responses — the name persists across turns via the session.
Environment variables:
AZURE_AI_PROJECT_ENDPOINT — Your Azure AI Foundry project endpoint
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME — Model deployment name (e.g. gpt-4o)
"""
@@ -68,19 +59,21 @@ class UserMemoryProvider(BaseContextProvider):
text = msg.text if hasattr(msg, "text") else ""
if isinstance(text, str) and "my name is" in text.lower():
state["user_name"] = text.lower().split("my name is")[-1].strip().split()[0].capitalize()
# </context_provider>
async def main() -> None:
# <create_agent>
credential = AzureCliCredential()
client = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"],
credential=credential,
client = FoundryChatClient(
project_endpoint="https://your-project.services.ai.azure.com",
model="gpt-4o",
credential=AzureCliCredential(),
)
agent = client.as_agent(
agent = Agent(
client=client,
name="MemoryAgent",
instructions="You are a friendly assistant.",
context_providers=[UserMemoryProvider()],
python/samples/01-get-started/05_first_workflow.py
+2
View File
@@ -45,6 +45,8 @@ def create_workflow():
"""Build the workflow: UpperCase → reverse_text."""
upper = UpperCase(id="upper_case")
return WorkflowBuilder(start_executor=upper).add_edge(upper, reverse_text).build()
# </create_workflow>
python/samples/01-get-started/06_host_your_agent.py
+10 -18
View File
@@ -4,45 +4,37 @@
# fmt: off
from typing import Any
from agent_framework.azure import AgentFunctionApp, AzureOpenAIChatClient
from agent_framework import Agent
from agent_framework.azure import AgentFunctionApp
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
# Load environment variables from .env file
load_dotenv()
"""Host your agent with Azure Functions.
This sample shows the Python hosting pattern used in docs:
- Create an agent with `AzureOpenAIChatClient`
- Create an agent with `FoundryChatClient`
- Register it with `AgentFunctionApp`
- Run with Azure Functions Core Tools (`func start`)
Prerequisites:
pip install agent-framework-azurefunctions --pre
Environment variables:
AZURE_OPENAI_ENDPOINT
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME
"""
# <create_agent>
def _create_agent() -> Any:
"""Create a hosted agent backed by Azure OpenAI."""
return AzureOpenAIChatClient(credential=AzureCliCredential()).as_agent(
return Agent(
client=FoundryChatClient(
project_endpoint="https://your-project.services.ai.azure.com",
model="gpt-4o",
credential=AzureCliCredential(),
),
name="HostedAgent",
instructions="You are a helpful assistant hosted in Azure Functions.",
)
# </create_agent>
# <host_agent>
app = AgentFunctionApp(agents=[_create_agent()], enable_health_check=True, max_poll_retries=50)
# </host_agent>
if __name__ == "__main__":
print("Start the Functions host with: func start")
print("Then call: POST /api/agents/HostedAgent/run")