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/03-workflows/agents/azure_ai_agents_streaming.py
+10 -8
View File
@@ -3,8 +3,8 @@
import asyncio
import os
from agent_framework import AgentResponseUpdate, WorkflowBuilder
from agent_framework.azure import AzureOpenAIResponsesClient
from agent_framework import Agent, AgentResponseUpdate, WorkflowBuilder
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
@@ -17,7 +17,7 @@ Sample: Azure AI Agents in a Workflow with Streaming
This sample shows how to create agents backed by Azure OpenAI Responses and use them in a workflow with streaming.
Prerequisites:
- AZURE_AI_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- AZURE_AI_MODEL_DEPLOYMENT_NAME must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
- Basic familiarity with WorkflowBuilder, edges, events, and streaming runs.
@@ -25,21 +25,23 @@ Prerequisites:
async def main() -> None:
client = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
)
# Create two agents: a Writer and a Reviewer.
writer_agent = client.as_agent(
writer_agent = Agent(
client=client,
name="Writer",
instructions=(
"You are an excellent content writer. You create new content and edit contents based on the feedback."
),
)
reviewer_agent = client.as_agent(
reviewer_agent = Agent(
client=client,
name="Reviewer",
instructions=(
"You are an excellent content reviewer. "
python/samples/03-workflows/agents/azure_ai_agents_with_shared_session.py
+11 -8
View File
@@ -4,6 +4,7 @@ import asyncio
import os
from agent_framework import (
Agent,
AgentExecutor,
AgentExecutorRequest,
AgentExecutorResponse,
@@ -13,7 +14,7 @@ from agent_framework import (
WorkflowRunState,
executor,
)
from agent_framework.azure import AzureOpenAIResponsesClient
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
@@ -33,11 +34,11 @@ Notes:
- Not all agents can share threads; usually only the same type of agents can share threads.
Demonstrate:
- Creating multiple agents with AzureOpenAIResponsesClient.
- Creating multiple agents with FoundryChatClient.
- Setting up a shared thread between agents.
Prerequisites:
- AZURE_AI_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- AZURE_AI_MODEL_DEPLOYMENT_NAME must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
- Basic familiarity with agents, workflows, and executors in the agent framework.
@@ -57,20 +58,22 @@ async def intercept_agent_response(
async def main() -> None:
client = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
)
# set the same context provider (same default source_id) for both agents to share the thread
writer = client.as_agent(
writer = Agent(
client=client,
instructions=("You are a concise copywriter. Provide a single, punchy marketing sentence based on the prompt."),
name="writer",
context_providers=[InMemoryHistoryProvider()],
)
reviewer = client.as_agent(
reviewer = Agent(
client=client,
instructions=("You are a thoughtful reviewer. Give brief feedback on the previous assistant message."),
name="reviewer",
context_providers=[InMemoryHistoryProvider()],
python/samples/03-workflows/agents/azure_chat_agents_and_executor.py
+16 -13
View File
@@ -5,6 +5,7 @@ import os
from typing import Final
from agent_framework import (
Agent,
AgentExecutorRequest,
AgentExecutorResponse,
AgentResponseUpdate,
@@ -13,7 +14,7 @@ from agent_framework import (
WorkflowContext,
executor,
)
from agent_framework.azure import AzureOpenAIResponsesClient
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
@@ -35,8 +36,8 @@ Demonstrates:
- Consuming an AgentExecutorResponse and forwarding an AgentExecutorRequest for the next agent.
Prerequisites:
- AZURE_AI_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for AzureOpenAIResponsesClient with required environment variables.
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- Authentication via azure-identity. Run `az login` before executing.
"""
@@ -100,22 +101,24 @@ async def enrich_with_references(
async def main() -> None:
"""Run the workflow and stream combined updates from both agents."""
# Create the agents
research_agent = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
).as_agent(
research_agent = Agent(
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
),
name="research_agent",
instructions=(
"Produce a short, bullet-style briefing with two actionable ideas. Label the section as 'Initial Draft'."
),
)
final_editor_agent = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
).as_agent(
final_editor_agent = Agent(
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
),
name="final_editor_agent",
instructions=(
"Use all conversation context (including external notes) to produce the final answer. "
python/samples/03-workflows/agents/azure_chat_agents_streaming.py
+16 -12
View File
@@ -3,8 +3,8 @@
import asyncio
import os
from agent_framework import AgentResponseUpdate, WorkflowBuilder
from agent_framework.azure import AzureOpenAIResponsesClient
from agent_framework import Agent, AgentResponseUpdate, WorkflowBuilder
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
@@ -17,8 +17,8 @@ Sample: AzureOpenAI Chat Agents in a Workflow with Streaming
This sample shows how to create AzureOpenAI Chat Agents and use them in a workflow with streaming.
Prerequisites:
- AZURE_AI_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for AzureOpenAIResponsesClient with required environment variables.
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
- Basic familiarity with WorkflowBuilder, edges, events, and streaming runs.
"""
@@ -27,22 +27,26 @@ Prerequisites:
async def main():
"""Build and run a simple two node agent workflow: Writer then Reviewer."""
# Create the agents
writer_agent = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
_writer_client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
).as_agent(
)
writer_agent = Agent(
client=_writer_client,
instructions=(
"You are an excellent content writer. You create new content and edit contents based on the feedback."
),
name="writer",
)
reviewer_agent = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
_reviewer_client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
).as_agent(
)
reviewer_agent = Agent(
client=_reviewer_client,
instructions=(
"You are an excellent content reviewer."
"Provide actionable feedback to the writer about the provided content."
python/samples/03-workflows/agents/azure_chat_agents_tool_calls_with_feedback.py
+15 -15
View File
@@ -22,7 +22,7 @@ from agent_framework import (
response_handler,
tool,
)
from agent_framework.azure import AzureOpenAIResponsesClient
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
from pydantic import Field
@@ -48,8 +48,8 @@ Demonstrates:
- Streaming AgentRunUpdateEvent updates alongside human-in-the-loop pauses.
Prerequisites:
- AZURE_AI_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for AzureOpenAIResponsesClient with required environment variables.
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- Authentication via azure-identity. Run `az login` before executing.
"""
@@ -175,13 +175,12 @@ class Coordinator(Executor):
def create_writer_agent() -> Agent:
"""Creates a writer agent with tools."""
return AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
# This sample has been tested only on `gpt-5.1` and may not work as intended on other models
# This sample is known to fail on `gpt-5-mini` reasoning input (GH issue #4059)
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
).as_agent(
return Agent(
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
),
name="writer_agent",
instructions=(
"You are a marketing writer. Call the available tools before drafting copy so you are precise. "
@@ -195,11 +194,12 @@ def create_writer_agent() -> Agent:
def create_final_editor_agent() -> Agent:
"""Creates a final editor agent."""
return AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
).as_agent(
return Agent(
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
),
name="final_editor_agent",
instructions=(
"You are an editor who polishes marketing copy after human approval. "
python/samples/03-workflows/agents/concurrent_workflow_as_agent.py
+17 -14
View File
@@ -1,9 +1,9 @@
# 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 agent_framework.orchestrations import ConcurrentBuilder
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
@@ -15,30 +15,31 @@ load_dotenv()
Sample: Build a concurrent workflow orchestration and wrap it as an agent.
This script wires up a fan-out/fan-in workflow using `ConcurrentBuilder`, and then
invokes the entire orchestration through the `workflow.as_agent(...)` interface so
invokes the entire orchestration through the `Agent(client=workflow,...)` interface so
downstream coordinators can reuse the orchestration as a single agent.
Demonstrates:
- Fan-out to multiple agents, fan-in aggregation of final ChatMessages.
- Reusing the orchestrated workflow as an agent entry point with `workflow.as_agent(...)`.
- Reusing the orchestrated workflow as an agent entry point with `Agent(client=workflow,...)`.
- Workflow completion when idle with no pending work
Prerequisites:
- AZURE_AI_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI access configured for AzureOpenAIResponsesClient (use az login + env vars)
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI access configured for FoundryChatClient (use az login + env vars)
- Familiarity with Workflow events (WorkflowEvent with type "output")
"""
async def main() -> None:
# 1) Create three domain agents using AzureOpenAIResponsesClient
client = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
# 1) Create three domain agents using FoundryChatClient
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
)
researcher = client.as_agent(
researcher = Agent(
client=client,
instructions=(
"You're an expert market and product researcher. Given a prompt, provide concise, factual insights,"
" opportunities, and risks."
@@ -46,7 +47,8 @@ async def main() -> None:
name="researcher",
)
marketer = client.as_agent(
marketer = Agent(
client=client,
instructions=(
"You're a creative marketing strategist. Craft compelling value propositions and target messaging"
" aligned to the prompt."
@@ -54,7 +56,8 @@ async def main() -> None:
name="marketer",
)
legal = client.as_agent(
legal = Agent(
client=client,
instructions=(
"You're a cautious legal/compliance reviewer. Highlight constraints, disclaimers, and policy concerns"
" based on the prompt."
@@ -66,7 +69,7 @@ async def main() -> None:
workflow = ConcurrentBuilder(participants=[researcher, marketer, legal]).build()
# 3) Expose the concurrent workflow as an agent for easy reuse
agent = workflow.as_agent(name="ConcurrentWorkflowAgent")
agent = Agent(client=workflow, name="ConcurrentWorkflowAgent")
prompt = "We are launching a new budget-friendly electric bike for urban commuters."
agent_response = await agent.run(prompt)
python/samples/03-workflows/agents/custom_agent_executors.py
+17 -15
View File
@@ -11,7 +11,7 @@ from agent_framework import (
WorkflowContext,
handler,
)
from agent_framework.azure import AzureOpenAIResponsesClient
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
@@ -25,15 +25,15 @@ This sample uses two custom executors. A Writer agent creates or edits content,
then hands the conversation to a Reviewer agent which evaluates and finalizes the result.
Purpose:
Show how to wrap chat agents created by AzureOpenAIResponsesClient inside workflow executors. Demonstrate the @handler
Show how to wrap chat agents created by FoundryChatClient inside workflow executors. Demonstrate the @handler
pattern with typed inputs and typed WorkflowContext[T] outputs, connect executors with the fluent WorkflowBuilder,
and finish by yielding outputs from the terminal node.
Note: When an agent is passed to a workflow, the workflow wraps the agent in a more sophisticated executor.
Prerequisites:
- AZURE_AI_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for AzureOpenAIResponsesClient with required environment variables.
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
- Basic familiarity with WorkflowBuilder, executors, edges, events, and streaming or non streaming runs.
"""
@@ -50,12 +50,13 @@ class Writer(Executor):
agent: Agent
def __init__(self, id: str = "writer"):
# Create a domain specific agent using your configured AzureOpenAIResponsesClient.
self.agent = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
).as_agent(
# Create a domain specific agent using your configured FoundryChatClient.
self.agent = Agent(
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
),
instructions=(
"You are an excellent content writer. You create new content and edit contents based on the feedback."
),
@@ -97,11 +98,12 @@ class Reviewer(Executor):
def __init__(self, id: str = "reviewer"):
# Create a domain specific agent that evaluates and refines content.
self.agent = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
).as_agent(
self.agent = Agent(
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
),
instructions=(
"You are an excellent content reviewer. You review the content and provide feedback to the writer."
),
python/samples/03-workflows/agents/group_chat_workflow_as_agent.py
+18 -15
View File
@@ -4,7 +4,7 @@ import asyncio
import os
from agent_framework import Agent
from agent_framework.azure import AzureOpenAIResponsesClient
from agent_framework.foundry import FoundryChatClient
from agent_framework.orchestrations import GroupChatBuilder
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
@@ -20,8 +20,8 @@ What it does:
- The orchestrator coordinates a researcher (chat completions) and a writer (responses API) to solve a task.
Prerequisites:
- AZURE_AI_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Environment variables configured for `AzureOpenAIResponsesClient`.
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Environment variables configured for `FoundryChatClient`.
"""
@@ -30,9 +30,9 @@ async def main() -> None:
name="Researcher",
description="Collects relevant background information.",
instructions="Gather concise facts that help a teammate answer the question.",
client=AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
),
)
@@ -41,23 +41,26 @@ async def main() -> None:
name="Writer",
description="Synthesizes a polished answer using the gathered notes.",
instructions="Compose clear and structured answers using any notes provided.",
client=AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
),
)
_orch_client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
)
# intermediate_outputs=True: Enable intermediate outputs to observe the conversation as it unfolds
# (Intermediate outputs will be emitted as WorkflowOutputEvent events)
workflow = GroupChatBuilder(
participants=[researcher, writer],
intermediate_outputs=True,
orchestrator_agent=AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
).as_agent(
orchestrator_agent=Agent(
client=_orch_client,
name="Orchestrator",
instructions="You coordinate a team conversation to solve the user's task.",
),
@@ -69,7 +72,7 @@ async def main() -> None:
print(f"Input: {task}\n")
try:
workflow_agent = workflow.as_agent(name="GroupChatWorkflowAgent")
workflow_agent = Agent(client=workflow, name="GroupChatWorkflowAgent")
agent_result = await workflow_agent.run(task)
if agent_result.messages:
python/samples/03-workflows/agents/handoff_workflow_as_agent.py
+31 -26
View File
@@ -12,7 +12,7 @@ from agent_framework import (
WorkflowAgent,
tool,
)
from agent_framework.azure import AzureOpenAIResponsesClient
from agent_framework.foundry import FoundryChatClient
from agent_framework.orchestrations import HandoffAgentUserRequest, HandoffBuilder
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
@@ -29,9 +29,9 @@ A handoff workflow defines a pattern that assembles agents in a mesh topology, a
them to transfer control to each other based on the conversation context.
Prerequisites:
- AZURE_AI_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- `az login` (Azure CLI authentication)
- Environment variables configured for AzureOpenAIResponsesClient (AZURE_AI_MODEL_DEPLOYMENT_NAME)
- Environment variables configured for FoundryChatClient (AZURE_AI_MODEL_DEPLOYMENT_NAME)
Key Concepts:
- Auto-registered handoff tools: HandoffBuilder automatically creates handoff tools
@@ -63,17 +63,18 @@ def process_return(order_number: Annotated[str, "Order number to process return
return f"Return initiated successfully for order {order_number}. You will receive return instructions via email."
def create_agents(client: AzureOpenAIResponsesClient) -> tuple[Agent, Agent, Agent, Agent]:
def create_agents(client: FoundryChatClient) -> tuple[Agent, Agent, Agent, Agent]:
"""Create and configure the triage and specialist agents.
Args:
client: The AzureOpenAIResponsesClient to use for creating agents.
client: The FoundryChatClient to use for creating agents.
Returns:
Tuple of (triage_agent, refund_agent, order_agent, return_agent)
"""
# Triage agent: Acts as the frontline dispatcher
triage_agent = client.as_agent(
triage_agent = Agent(
client=client,
instructions=(
"You are frontline support triage. Route customer issues to the appropriate specialist agents "
"based on the problem described."
@@ -82,7 +83,8 @@ def create_agents(client: AzureOpenAIResponsesClient) -> tuple[Agent, Agent, Age
)
# Refund specialist: Handles refund requests
refund_agent = client.as_agent(
refund_agent = Agent(
client=client,
instructions="You process refund requests.",
name="refund_agent",
# In a real application, an agent can have multiple tools; here we keep it simple
@@ -90,7 +92,8 @@ def create_agents(client: AzureOpenAIResponsesClient) -> tuple[Agent, Agent, Age
)
# Order/shipping specialist: Resolves delivery issues
order_agent = client.as_agent(
order_agent = Agent(
client=client,
instructions="You handle order and shipping inquiries.",
name="order_agent",
# In a real application, an agent can have multiple tools; here we keep it simple
@@ -98,7 +101,8 @@ def create_agents(client: AzureOpenAIResponsesClient) -> tuple[Agent, Agent, Age
)
# Return specialist: Handles return requests
return_agent = client.as_agent(
return_agent = Agent(
client=client,
instructions="You manage product return requests.",
name="return_agent",
# In a real application, an agent can have multiple tools; here we keep it simple
@@ -153,9 +157,9 @@ async def main() -> None:
replace the scripted_responses with actual user input collection.
"""
# Initialize the Azure OpenAI chat client
client = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
)
@@ -170,20 +174,21 @@ async def main() -> None:
# Without this, the default behavior continues requesting user input until max_turns
# is reached. Here we use a custom condition that checks if the conversation has ended
# naturally (when one of the agents says something like "you're welcome").
agent = (
HandoffBuilder(
name="customer_support_handoff",
participants=[triage, refund, order, support],
# Custom termination: Check if one of the agents has provided a closing message.
# This looks for the last message containing "welcome", which indicates the
# conversation has concluded naturally.
termination_condition=lambda conversation: (
len(conversation) > 0 and "welcome" in conversation[-1].text.lower()
),
)
.with_start_agent(triage)
.build()
.as_agent() # Convert workflow to agent interface
agent = Agent(
client=(
HandoffBuilder(
name="customer_support_handoff",
participants=[triage, refund, order, support],
# Custom termination: Check if one of the agents has provided a closing message.
# This looks for the last message containing "welcome", which indicates the
# conversation has concluded naturally.
termination_condition=lambda conversation: (
len(conversation) > 0 and "welcome" in conversation[-1].text.lower()
),
)
.with_start_agent(triage)
.build()
),
)
# Scripted user responses for reproducible demo
python/samples/03-workflows/agents/magentic_workflow_as_agent.py
+14 -14
View File
@@ -6,7 +6,7 @@ import os
from agent_framework import (
Agent,
)
from agent_framework.azure import AzureOpenAIResponsesClient
from agent_framework.foundry import FoundryChatClient
from agent_framework.orchestrations import MagenticBuilder
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
@@ -18,12 +18,12 @@ load_dotenv()
Sample: Build a Magentic orchestration and wrap it as an agent.
The script configures a Magentic workflow with streaming callbacks, then invokes the
orchestration through `workflow.as_agent(...)` so the entire Magentic loop can be reused
orchestration through `Agent(client=workflow, ...)` so the entire Magentic loop can be reused
like any other agent while still emitting callback telemetry.
Prerequisites:
- AZURE_AI_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- OpenAI credentials configured for `AzureOpenAIResponsesClient` and `AzureOpenAIResponsesClient`.
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- OpenAI credentials configured for `FoundryChatClient` and `FoundryChatClient`.
"""
@@ -35,17 +35,17 @@ async def main() -> None:
"You are a Researcher. You find information without additional computation or quantitative analysis."
),
# This agent requires the gpt-4o-search-preview model to perform web searches.
client=AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
),
)
# Create code interpreter tool using instance method
coder_client = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
coder_client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
)
code_interpreter_tool = coder_client.get_code_interpreter_tool()
@@ -63,9 +63,9 @@ async def main() -> None:
name="MagenticManager",
description="Orchestrator that coordinates the research and coding workflow",
instructions="You coordinate a team to complete complex tasks efficiently.",
client=AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
),
)
@@ -98,7 +98,7 @@ async def main() -> None:
try:
# Wrap the workflow as an agent for composition scenarios
print("\nWrapping workflow as an agent and running...")
workflow_agent = workflow.as_agent(name="MagenticWorkflowAgent")
workflow_agent = Agent(client=workflow, name="MagenticWorkflowAgent")
last_response_id: str | None = None
async for update in workflow_agent.run(task, stream=True):
python/samples/03-workflows/agents/sequential_workflow_as_agent.py
+13 -11
View File
@@ -1,9 +1,9 @@
# 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 agent_framework.orchestrations import SequentialBuilder
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
@@ -15,7 +15,7 @@ load_dotenv()
Sample: Build a sequential workflow orchestration and wrap it as an agent.
The script assembles a sequential conversation flow with `SequentialBuilder`, then
invokes the entire orchestration through the `workflow.as_agent(...)` interface so
invokes the entire orchestration through the `Agent(client=workflow,...)` interface so
other coordinators can reuse the chain as a single participant.
Note on internal adapters:
@@ -26,25 +26,27 @@ Note on internal adapters:
You can safely ignore them when focusing on agent progress.
Prerequisites:
- AZURE_AI_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI access configured for AzureOpenAIResponsesClient (use az login + env vars)
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI access configured for FoundryChatClient (use az login + env vars)
"""
async def main() -> None:
# 1) Create agents
client = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
)
writer = client.as_agent(
writer = Agent(
client=client,
instructions=("You are a concise copywriter. Provide a single, punchy marketing sentence based on the prompt."),
name="writer",
)
reviewer = client.as_agent(
reviewer = Agent(
client=client,
instructions=("You are a thoughtful reviewer. Give brief feedback on the previous assistant message."),
name="reviewer",
)
@@ -53,7 +55,7 @@ async def main() -> None:
workflow = SequentialBuilder(participants=[writer, reviewer]).build()
# 3) Treat the workflow itself as an agent for follow-up invocations
agent = workflow.as_agent(name="SequentialWorkflowAgent")
agent = Agent(client=workflow, name="SequentialWorkflowAgent")
prompt = "Write a tagline for a budget-friendly eBike."
agent_response = await agent.run(prompt)
python/samples/03-workflows/agents/workflow_as_agent_human_in_the_loop.py
+9 -12
View File
@@ -8,7 +8,8 @@ from dataclasses import dataclass
from pathlib import Path
from typing import Any
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
@@ -48,8 +49,8 @@ to a human, receives the human response, and then forwards that response back
to the Worker. The workflow completes when idle.
Prerequisites:
- AZURE_AI_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- OpenAI account configured and accessible for AzureOpenAIResponsesClient.
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- OpenAI account configured and accessible for FoundryChatClient.
- Familiarity with WorkflowBuilder, Executor, and WorkflowContext from agent_framework.
- Understanding of request-response message handling in executors.
- (Optional) Review of reflection and escalation patterns, such as those in
@@ -110,20 +111,16 @@ async def main() -> None:
# and escalation paths for human review.
worker = Worker(
id="worker",
client=AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
),
)
reviewer = ReviewerWithHumanInTheLoop(worker_id="worker")
agent = (
WorkflowBuilder(start_executor=worker)
.add_edge(worker, reviewer) # Worker sends requests to Reviewer
.add_edge(reviewer, worker) # Reviewer sends feedback to Worker
.build()
.as_agent() # Convert workflow into an agent interface
agent = Agent(
client=(WorkflowBuilder(start_executor=worker).add_edge(worker, reviewer).add_edge(reviewer, worker).build()),
)
print("Running workflow agent with user query...")
python/samples/03-workflows/agents/workflow_as_agent_kwargs.py
+13 -12
View File
@@ -5,8 +5,8 @@ import json
import os
from typing import Annotated, Any
from agent_framework import tool
from agent_framework.azure import AzureOpenAIResponsesClient
from agent_framework import Agent, tool
from agent_framework.foundry import FoundryChatClient
from agent_framework.orchestrations import SequentialBuilder
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
@@ -19,22 +19,22 @@ load_dotenv()
Sample: Workflow as Agent with kwargs Propagation to @tool Tools
This sample demonstrates how to flow custom context (skill data, user tokens, etc.)
through a workflow exposed via .as_agent() to @tool functions using the **kwargs pattern.
through a workflow exposed Agent(client=via,) to @tool functions using the **kwargs pattern.
Key Concepts:
- Build a workflow using SequentialBuilder (or any builder pattern)
- Expose the workflow as a reusable agent via workflow.as_agent()
- Expose the workflow as a reusable agent via Agent(client=workflow,)
- Pass custom context as kwargs when invoking workflow_agent.run()
- kwargs are stored in State and propagated to all agent invocations
- @tool functions receive kwargs via **kwargs parameter
When to use workflow.as_agent():
When to use Agent(client=workflow,):
- To treat an entire workflow orchestration as a single agent
- To compose workflows into higher-level orchestrations
- To maintain a consistent agent interface for callers
Prerequisites:
- AZURE_AI_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Environment variables configured
"""
@@ -87,14 +87,15 @@ async def main() -> None:
print("=" * 70)
# Create chat client
client = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
)
# Create agent with tools that use kwargs
agent = client.as_agent(
agent = Agent(
client=client,
name="assistant",
instructions=(
"You are a helpful assistant. Use the available tools to help users. "
@@ -107,8 +108,8 @@ async def main() -> None:
# Build a sequential workflow
workflow = SequentialBuilder(participants=[agent]).build()
# Expose the workflow as an agent using .as_agent()
workflow_agent = workflow.as_agent(name="WorkflowAgent")
# Expose the workflow as an agent Agent(client=using,)
workflow_agent = Agent(client=workflow, name="WorkflowAgent")
# Define custom context that will flow to tools via kwargs
custom_data = {
python/samples/03-workflows/agents/workflow_as_agent_reflection_pattern.py
+12 -15
View File
@@ -6,6 +6,7 @@ from dataclasses import dataclass
from uuid import uuid4
from agent_framework import (
Agent,
AgentResponse,
Executor,
Message,
@@ -14,7 +15,7 @@ from agent_framework import (
WorkflowContext,
handler,
)
from agent_framework.azure import AzureOpenAIResponsesClient
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
from pydantic import BaseModel
@@ -39,8 +40,8 @@ Key Concepts Demonstrated:
- State management for pending requests and retry logic.
Prerequisites:
- AZURE_AI_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- OpenAI account configured and accessible for AzureOpenAIResponsesClient.
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- OpenAI account configured and accessible for FoundryChatClient.
- Familiarity with WorkflowBuilder, Executor, WorkflowContext, and event handling.
- Understanding of how agent messages are generated, reviewed, and re-submitted.
"""
@@ -195,27 +196,23 @@ async def main() -> None:
print("Building workflow with Worker ↔ Reviewer cycle...")
worker = Worker(
id="worker",
client=AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
),
)
reviewer = Reviewer(
id="reviewer",
client=AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
),
)
agent = (
WorkflowBuilder(start_executor=worker)
.add_edge(worker, reviewer) # Worker sends responses to Reviewer
.add_edge(reviewer, worker) # Reviewer provides feedback to Worker
.build()
.as_agent() # Wrap workflow as an agent
agent = Agent(
client=(WorkflowBuilder(start_executor=worker).add_edge(worker, reviewer).add_edge(reviewer, worker).build()),
)
print("Running workflow agent with user query...")
python/samples/03-workflows/agents/workflow_as_agent_with_session.py
+19 -16
View File
@@ -3,8 +3,8 @@
import asyncio
import os
from agent_framework import AgentSession, InMemoryHistoryProvider
from agent_framework.azure import AzureOpenAIResponsesClient
from agent_framework import Agent, AgentSession, InMemoryHistoryProvider
from agent_framework.foundry import FoundryChatClient
from agent_framework.orchestrations import SequentialBuilder
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
@@ -24,7 +24,7 @@ It also demonstrates how to enable checkpointing for workflow execution state
persistence, allowing workflows to be paused and resumed.
Key concepts:
- Workflows can be wrapped as agents using workflow.as_agent()
- Workflows can be wrapped as agents using Agent(client=workflow,)
- AgentSession preserves conversation history
- Each call to agent.run() includes session history + new message
- Participants in the workflow see the full conversation context
@@ -37,20 +37,21 @@ Use cases:
- Long-running workflows that need pause/resume capability
Prerequisites:
- AZURE_AI_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Environment variables configured for AzureOpenAIResponsesClient
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Environment variables configured for FoundryChatClient
"""
async def main() -> None:
# Create a chat client
client = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
)
assistant = client.as_agent(
assistant = Agent(
client=client,
name="assistant",
instructions=(
"You are a helpful assistant. Answer questions based on the conversation "
@@ -58,7 +59,8 @@ async def main() -> None:
),
)
summarizer = client.as_agent(
summarizer = Agent(
client=client,
name="summarizer",
instructions=(
"You are a summarizer. After the assistant responds, provide a brief "
@@ -70,7 +72,7 @@ async def main() -> None:
workflow = SequentialBuilder(participants=[assistant, summarizer]).build()
# Wrap the workflow as an agent
agent = workflow.as_agent(name="ConversationalWorkflowAgent")
agent = Agent(client=workflow, name="ConversationalWorkflowAgent")
# Create a session to maintain history
session = agent.create_session()
@@ -129,19 +131,20 @@ async def demonstrate_session_serialization() -> None:
This shows how conversation history can be persisted and restored,
enabling long-running conversational workflows.
"""
client = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=AzureCliCredential(),
)
memory_assistant = client.as_agent(
memory_assistant = Agent(
client=client,
name="memory_assistant",
instructions="You are a helpful assistant with good memory. Remember details from our conversation.",
)
workflow = SequentialBuilder(participants=[memory_assistant]).build()
agent = workflow.as_agent(name="MemoryWorkflowAgent")
agent = Agent(client=workflow, name="MemoryWorkflowAgent")
# Create initial session and have a conversation
session = agent.create_session()