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>
2026-06-16 21:04:09 +08:00 · 2026-03-25 10:56:29 +01:00
parent 4b533608b6
commit 5e056b672e
485 changed files with 9784 additions and 12084 deletions
@@ -4,7 +4,7 @@ import os
 from datetime import datetime, timezone

 from agent_framework import Agent, InMemoryHistoryProvider
-from agent_framework.azure import AzureOpenAIResponsesClient, FoundryMemoryProvider
+from agent_framework.foundry import FoundryChatClient, FoundryMemoryProvider
 from azure.ai.projects.aio import AIProjectClient
 from azure.ai.projects.models import (
    MemoryStoreDefaultDefinition,
@@ -31,8 +31,8 @@ so that follow-up responses demonstrate the agent relying solely on Foundry Memo
 rather than chat history. The memory store is deleted at the end of the run.

 Prerequisites:
-1. Set AZURE_AI_PROJECT_ENDPOINT environment variable
-2. Set AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME for the chat/responses model
+1. Set FOUNDRY_PROJECT_ENDPOINT environment variable
+2. Set FOUNDRY_MODEL for the chat/responses model
 3. Set AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME for the embedding model
 4. Deploy both a chat model (e.g. gpt-4) and an embedding model (e.g. text-embedding-3-small)
 """
@@ -40,7 +40,7 @@ load_dotenv()


 async def main() -> None:
-    endpoint = os.environ["AZURE_AI_PROJECT_ENDPOINT"]
+    endpoint = os.environ["FOUNDRY_PROJECT_ENDPOINT"]
    async with (
        AzureCliCredential() as credential,
        AIProjectClient(endpoint=endpoint, credential=credential) as project_client,
@@ -54,7 +54,7 @@ async def main() -> None:
            user_profile_details="Avoid irrelevant or sensitive data, such as age, financials, precise location, and credentials",
        )
        memory_store_definition = MemoryStoreDefaultDefinition(
-            chat_model=os.environ["AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"],
+            chat_model=os.environ["FOUNDRY_MODEL"],
            embedding_model=os.environ["AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME"],
            options=options,
        )
@@ -75,7 +75,7 @@ async def main() -> None:
        print("==========================================")

        # Create the chat client
-        client = AzureOpenAIResponsesClient(project_client=project_client)
+        client = FoundryChatClient(project_client=project_client)
        # Create the Foundry Memory context provider
        memory_provider = FoundryMemoryProvider(
            project_client=project_client,
@@ -8,13 +8,13 @@ This folder contains examples demonstrating how to use the Azure AI Search conte

 | File | Description |
 |------|-------------|
-| [`azure_ai_with_search_context_agentic.py`](azure_ai_with_search_context_agentic.py) | **Agentic mode** (recommended for most scenarios): Uses Knowledge Bases in Azure AI Search for query planning and multi-hop reasoning. Provides more accurate results through intelligent retrieval with automatic query reformulation. Slightly slower with more token consumption for query planning. [Learn more](https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/foundry-iq-boost-response-relevance-by-36-with-agentic-retrieval/4470720) |
-| [`azure_ai_with_search_context_semantic.py`](azure_ai_with_search_context_semantic.py) | **Semantic mode** (fast queries): Fast hybrid search combining vector and keyword search with semantic ranking. Returns raw search results as context. Best for scenarios where speed is critical and simple retrieval is sufficient. |
+| [`search_context_agentic.py`](search_context_agentic.py) | **Agentic mode** (recommended for most scenarios): Uses Knowledge Bases in Azure AI Search for query planning and multi-hop reasoning. Provides more accurate results through intelligent retrieval with automatic query reformulation. Slightly slower with more token consumption for query planning. [Learn more](https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/foundry-iq-boost-response-relevance-by-36-with-agentic-retrieval/4470720) |
+| [`search_context_semantic.py`](search_context_semantic.py) | **Semantic mode** (fast queries): Fast hybrid search combining vector and keyword search with semantic ranking. Returns raw search results as context. Best for scenarios where speed is critical and simple retrieval is sufficient. |

 ## Installation

 ```bash
-pip install agent-framework-azure-ai-search agent-framework-azure-ai
+pip install agent-framework-foundry-search agent-framework-foundry
 ```

 ## Prerequisites
@@ -4,7 +4,8 @@ import asyncio
 import os

 from agent_framework import Agent
-from agent_framework.azure import AzureAIAgentClient, AzureAISearchContextProvider
+from agent_framework.azure import AzureAISearchContextProvider
+from agent_framework.foundry import FoundryChatClient
 from azure.identity.aio import AzureCliCredential
 from dotenv import load_dotenv

@@ -31,8 +32,8 @@ Prerequisites:

 Environment variables:
   - AZURE_SEARCH_ENDPOINT: Your Azure AI Search endpoint
-   - AZURE_SEARCH_API_KEY: (Optional) API key - if not provided, uses DefaultAzureCredential
-   - AZURE_AI_PROJECT_ENDPOINT: Your Azure AI Foundry project endpoint
+   - AZURE_SEARCH_API_KEY: (Optional) API key - if not provided, uses AzureCliCredential
+   - FOUNDRY_PROJECT_ENDPOINT: Your Azure AI Foundry project endpoint
   - AZURE_AI_MODEL_DEPLOYMENT_NAME: Your model deployment name (e.g., "gpt-4o")

 For using an existing Knowledge Base (recommended):
@@ -57,7 +58,7 @@ async def main() -> None:
    # Get configuration from environment
    search_endpoint = os.environ["AZURE_SEARCH_ENDPOINT"]
    search_key = os.environ.get("AZURE_SEARCH_API_KEY")
-    project_endpoint = os.environ["AZURE_AI_PROJECT_ENDPOINT"]
+    project_endpoint = os.environ["FOUNDRY_PROJECT_ENDPOINT"]
    model_deployment = os.environ.get("AZURE_AI_MODEL_DEPLOYMENT_NAME", "gpt-4o")

    # Agentic mode requires exactly ONE of: knowledge_base_name OR index_name
@@ -99,7 +100,7 @@ async def main() -> None:
            credential=AzureCliCredential() if not search_key else None,
            mode="agentic",
            azure_openai_resource_url=azure_openai_resource_url,
-            model_deployment_name=model_deployment,
+            model_model=model_deployment,
            # Optional: Configure retrieval behavior
            knowledge_base_output_mode="extractive_data",  # or "answer_synthesis"
            retrieval_reasoning_effort="minimal",  # or "medium", "low"
@@ -109,9 +110,9 @@ async def main() -> None:
    # Create agent with search context provider
    async with (
        search_provider,
-        AzureAIAgentClient(
+        FoundryChatClient(
            project_endpoint=project_endpoint,
-            model_deployment_name=model_deployment,
+            model_model=model_deployment,
            credential=AzureCliCredential(),
        ) as client,
        Agent(
@@ -4,7 +4,8 @@ import asyncio
 import os

 from agent_framework import Agent
-from agent_framework.azure import AzureAIAgentClient, AzureAISearchContextProvider, AzureOpenAIEmbeddingClient
+from agent_framework.azure import AzureAISearchContextProvider, AzureOpenAIEmbeddingClient
+from agent_framework.foundry import FoundryChatClient
 from azure.identity.aio import AzureCliCredential
 from dotenv import load_dotenv

@@ -26,9 +27,9 @@ Prerequisites:
 2. An Azure AI Foundry project with a model deployment
 3. Set the following environment variables:
   - AZURE_SEARCH_ENDPOINT: Your Azure AI Search endpoint
-   - AZURE_SEARCH_API_KEY: (Optional) Your search API key - if not provided, uses DefaultAzureCredential for Entra ID
+   - AZURE_SEARCH_API_KEY: (Optional) Your search API key - if not provided, uses AzureCliCredential for Entra ID
   - AZURE_SEARCH_INDEX_NAME: Your search index name
-   - AZURE_AI_PROJECT_ENDPOINT: Your Azure AI Foundry project endpoint
+   - FOUNDRY_PROJECT_ENDPOINT: Your Azure AI Foundry project endpoint
   - AZURE_AI_MODEL_DEPLOYMENT_NAME: Your model deployment name (e.g., "gpt-4o")
   - AZURE_OPENAI_EMBEDDING_MODEL_ID: (Optional) Your embedding model for hybrid search (e.g., "text-embedding-3-small")
   - AZURE_OPENAI_ENDPOINT: (Optional) Your Azure OpenAI resource URL, required if using an OpenAI embedding model for hybrid search
@@ -51,7 +52,7 @@ async def main() -> None:
    search_endpoint = os.environ["AZURE_SEARCH_ENDPOINT"]
    search_key = os.environ.get("AZURE_SEARCH_API_KEY")
    index_name = os.environ["AZURE_SEARCH_INDEX_NAME"]
-    project_endpoint = os.environ["AZURE_AI_PROJECT_ENDPOINT"]
+    project_endpoint = os.environ["FOUNDRY_PROJECT_ENDPOINT"]
    model_deployment = os.environ.get("AZURE_AI_MODEL_DEPLOYMENT_NAME", "gpt-4o")
    openai_endpoint = os.environ.get("AZURE_OPENAI_ENDPOINT")
    embedding_model = os.environ.get("AZURE_OPENAI_EMBEDDING_MODEL_ID", "text-embedding-3-small")
@@ -60,7 +61,7 @@ async def main() -> None:
    if openai_endpoint and embedding_model:
        embedding_client = AzureOpenAIEmbeddingClient(
            endpoint=openai_endpoint,
-            deployment_name=embedding_model,
+            model=embedding_model,
            credential=credential,
        )

@@ -83,9 +84,9 @@ async def main() -> None:
    # Create agent with search context provider
    async with (
        search_provider,
-        AzureAIAgentClient(
+        FoundryChatClient(
            project_endpoint=project_endpoint,
-            model_deployment_name=model_deployment,
+            model_model=model_deployment,
            credential=credential,
        ) as client,
        Agent(
@@ -3,8 +3,8 @@
 import asyncio
 import uuid

-from agent_framework import tool
-from agent_framework.azure import AzureAIAgentClient
+from agent_framework import Agent, tool
+from agent_framework.foundry import FoundryChatClient
 from agent_framework.mem0 import Mem0ContextProvider
 from azure.identity.aio import AzureCliCredential
 from dotenv import load_dotenv
@@ -30,19 +30,17 @@ def retrieve_company_report(company_code: str, detailed: bool) -> str:

 async def main() -> None:
    """Example of memory usage with Mem0 context provider."""
-
    print("=== Mem0 Context Provider Example ===")
-
    # Each record in Mem0 should be associated with agent_id or user_id or application_id or thread_id.
    # In this example, we associate Mem0 records with user_id.
    user_id = str(uuid.uuid4())
-
    # For Azure authentication, run `az login` command in terminal or replace AzureCliCredential with preferred
    # authentication option.
    # For Mem0 authentication, set Mem0 API key via "api_key" parameter or MEM0_API_KEY environment variable.
    async with (
        AzureCliCredential() as credential,
-        AzureAIAgentClient(credential=credential).as_agent(
+        Agent(
+            client=FoundryChatClient(credential=credential),
            name="FriendlyAssistant",
            instructions="You are a friendly assistant.",
            tools=retrieve_company_report,
@@ -56,33 +54,23 @@ async def main() -> None:
        print(f"User: {query}")
        result = await agent.run(query)
        print(f"Agent: {result}\n")
-
        # Now tell the agent the company code and the report format that you want to use
        # and it should be able to invoke the tool and return the report.
        query = "I always work with CNTS and I always want a detailed report format. Please remember and retrieve it."
-        print(f"User: {query}")
-        result = await agent.run(query)
-        print(f"Agent: {result}\n")
-
        # Mem0 processes and indexes memories asynchronously.
        # Wait for memories to be indexed before querying in a new thread.
        # In production, consider implementing retry logic or using Mem0's
        # eventual consistency handling instead of a fixed delay.
        print("Waiting for memories to be processed...")
        await asyncio.sleep(12)  # Empirically determined delay for Mem0 indexing
-
        print("\nRequest within a new session:")
        # Create a new session for the agent.
        # The new session has no context of the previous conversation.
        session = agent.create_session()
-
        # Since we have the mem0 component in the session, the agent should be able to
        # retrieve the company report without asking for clarification, as it will
        # be able to remember the user preferences from Mem0 component.
-        query = "Please retrieve my company report"
-        print(f"User: {query}")
        result = await agent.run(query, session=session)
-        print(f"Agent: {result}\n")


 if __name__ == "__main__":
@@ -3,8 +3,8 @@
 import asyncio
 import uuid

-from agent_framework import tool
-from agent_framework.azure import AzureAIAgentClient
+from agent_framework import Agent, tool
+from agent_framework.foundry import FoundryChatClient
 from agent_framework.mem0 import Mem0ContextProvider
 from azure.identity.aio import AzureCliCredential
 from dotenv import load_dotenv
@@ -31,13 +31,10 @@ def retrieve_company_report(company_code: str, detailed: bool) -> str:

 async def main() -> None:
    """Example of memory usage with local Mem0 OSS context provider."""
-
    print("=== Mem0 Context Provider Example ===")
-
    # Each record in Mem0 should be associated with agent_id or user_id or application_id or thread_id.
    # In this example, we associate Mem0 records with user_id.
    user_id = str(uuid.uuid4())
-
    # For Azure authentication, run `az login` command in terminal or replace AzureCliCredential with preferred
    # authentication option.
    # By default, local Mem0 authenticates to your OpenAI using the OPENAI_API_KEY environment variable.
@@ -45,7 +42,8 @@ async def main() -> None:
    local_mem0_client = AsyncMemory()
    async with (
        AzureCliCredential() as credential,
-        AzureAIAgentClient(credential=credential).as_agent(
+        Agent(
+            client=FoundryChatClient(credential=credential),
            name="FriendlyAssistant",
            instructions="You are a friendly assistant.",
            tools=retrieve_company_report,
@@ -59,27 +57,17 @@ async def main() -> None:
        print(f"User: {query}")
        result = await agent.run(query)
        print(f"Agent: {result}\n")
-
        # Now tell the agent the company code and the report format that you want to use
        # and it should be able to invoke the tool and return the report.
        query = "I always work with CNTS and I always want a detailed report format. Please remember and retrieve it."
-        print(f"User: {query}")
-        result = await agent.run(query)
-        print(f"Agent: {result}\n")
-
        print("\nRequest within a new session:")
-
        # Create a new session for the agent.
        # The new session has no context of the previous conversation.
        session = agent.create_session()
-
        # Since we have the mem0 component in the session, the agent should be able to
        # retrieve the company report without asking for clarification, as it will
        # be able to remember the user preferences from Mem0 component.
-        query = "Please retrieve my company report"
-        print(f"User: {query}")
        result = await agent.run(query, session=session)
-        print(f"Agent: {result}\n")


 if __name__ == "__main__":
@@ -3,8 +3,8 @@
 import asyncio
 import uuid

-from agent_framework import tool
-from agent_framework.azure import AzureAIAgentClient
+from agent_framework import Agent, tool
+from agent_framework.foundry import FoundryChatClient
 from agent_framework.mem0 import Mem0ContextProvider
 from azure.identity.aio import AzureCliCredential
 from dotenv import load_dotenv
@@ -37,7 +37,8 @@ async def example_global_thread_scope() -> None:

    async with (
        AzureCliCredential() as credential,
-        AzureAIAgentClient(credential=credential).as_agent(
+        Agent(
+            client=FoundryChatClient(credential=credential),
            name="GlobalMemoryAssistant",
            instructions="You are an assistant that remembers user preferences across conversations.",
            tools=get_user_preferences,
@@ -78,7 +79,8 @@ async def example_per_operation_thread_scope() -> None:

    async with (
        AzureCliCredential() as credential,
-        AzureAIAgentClient(credential=credential).as_agent(
+        Agent(
+            client=FoundryChatClient(credential=credential),
            name="ScopedMemoryAssistant",
            instructions="You are an assistant with thread-scoped memory.",
            tools=get_user_preferences,
@@ -129,7 +131,8 @@ async def example_multiple_agents() -> None:

    async with (
        AzureCliCredential() as credential,
-        AzureAIAgentClient(credential=credential).as_agent(
+        Agent(
+            client=FoundryChatClient(credential=credential),
            name="PersonalAssistant",
            instructions="You are a personal assistant that helps with personal tasks.",
            context_providers=[
@@ -139,7 +142,8 @@ async def example_multiple_agents() -> None:
                )
            ],
        ) as personal_agent,
-        AzureAIAgentClient(credential=credential).as_agent(
+        Agent(
+            client=FoundryChatClient(credential=credential),
            name="WorkAssistant",
            instructions="You are a work assistant that helps with professional tasks.",
            context_providers=[
@@ -17,23 +17,22 @@ Requirements:

 Environment Variables:
  - AZURE_REDIS_HOST: Your Azure Managed Redis host (e.g., myredis.redis.cache.windows.net)
-  - AZURE_AI_PROJECT_ENDPOINT: Your Azure AI Foundry project endpoint
-  - AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME: Azure OpenAI Responses deployment name
+  - FOUNDRY_PROJECT_ENDPOINT: Your Azure AI Foundry project endpoint
+  - FOUNDRY_MODEL: Azure OpenAI Responses deployment name
  - AZURE_USER_OBJECT_ID: Your Azure AD User Object ID for authentication
 """

 import asyncio
 import os

-from agent_framework.azure import AzureOpenAIResponsesClient
+from agent_framework import Agent
+from agent_framework.foundry import FoundryChatClient
 from agent_framework.redis import RedisHistoryProvider
 from azure.identity import AzureCliCredential
 from azure.identity.aio import AzureCliCredential as AsyncAzureCliCredential
-from dotenv import load_dotenv
 from redis.credentials import CredentialProvider

-# Load environment variables from .env file
-load_dotenv()
+# Copyright (c) Microsoft. All rights reserved.


 class AzureCredentialProvider(CredentialProvider):
@@ -81,14 +80,15 @@ async def main() -> None:
    )

    # 3. Create chat client
-    client = AzureOpenAIResponsesClient(
-        project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
-        deployment_name=os.environ["AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"],
+    client = FoundryChatClient(
+        project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
+        model=os.environ["FOUNDRY_MODEL"],
        credential=AzureCliCredential(),
    )

    # 4. Create agent with Azure Redis history provider
-    agent = client.as_agent(
+    agent = Agent(
+        client=client,
        name="AzureRedisAssistant",
        instructions="You are a helpful assistant.",
        context_providers=[history_provider],
@@ -30,8 +30,8 @@ Run:
 import asyncio
 import os

-from agent_framework import Message, tool
-from agent_framework.azure import AzureOpenAIResponsesClient
+from agent_framework import Agent, Message, tool
+from agent_framework.foundry import FoundryChatClient
 from agent_framework.redis import RedisContextProvider
 from azure.identity import AzureCliCredential
 from dotenv import load_dotenv
@@ -99,11 +99,11 @@ def search_flights(origin_airport_code: str, destination_airport_code: str, deta
    )


-def create_chat_client() -> AzureOpenAIResponsesClient:
+def create_chat_client() -> FoundryChatClient:
    """Create an Azure OpenAI Responses client using a Foundry project endpoint."""
-    return AzureOpenAIResponsesClient(
-        project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
-        deployment_name=os.environ["AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"],
+    return FoundryChatClient(
+        project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
+        model=os.environ["FOUNDRY_MODEL"],
        credential=AzureCliCredential(),
    )

@@ -121,7 +121,7 @@ async def main() -> None:
    # Create a provider with partition scope and OpenAI embeddings

    # Please set OPENAI_API_KEY to use the OpenAI vectorizer.
-    # For chat responses, also set AZURE_AI_PROJECT_ENDPOINT and AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME.
+    # For chat responses, also set FOUNDRY_PROJECT_ENDPOINT and FOUNDRY_MODEL.

    # We attach an embedding vectorizer so the provider can perform hybrid (text + vector)
    # retrieval. If you prefer text-only retrieval, instantiate RedisContextProvider without the
@@ -206,7 +206,8 @@ async def main() -> None:
    client = create_chat_client()
    # Create agent wired to the Redis context provider. The provider automatically
    # persists conversational details and surfaces relevant context on each turn.
-    agent = client.as_agent(
+    agent = Agent(
+        client=client,
        name="MemoryEnhancedAssistant",
        instructions=(
            "You are a helpful assistant. Personalize replies using provided context. "
@@ -249,7 +250,8 @@ async def main() -> None:
    # Create agent exposing the flight search tool. Tool outputs are captured by the
    # provider and become retrievable context for later turns.
    client = create_chat_client()
-    agent = client.as_agent(
+    agent = Agent(
+        client=client,
        name="MemoryEnhancedAssistant",
        instructions=(
            "You are a helpful assistant. Personalize replies using provided context. "
@@ -21,15 +21,15 @@ Run:
 import asyncio
 import os

-from agent_framework.azure import AzureOpenAIResponsesClient
+from agent_framework import Agent
+from agent_framework.foundry import FoundryChatClient
 from agent_framework.redis import RedisContextProvider
 from azure.identity import AzureCliCredential
-from dotenv import load_dotenv
 from redisvl.extensions.cache.embeddings import EmbeddingsCache
 from redisvl.utils.vectorize import OpenAITextVectorizer

-# Load environment variables from .env file
-load_dotenv()
+# Copyright (c) Microsoft. All rights reserved.
+

 # Default Redis URL for local Redis Stack.
 # Override via the REDIS_URL environment variable for remote or authenticated instances.
@@ -64,14 +64,15 @@ async def main() -> None:
    )

    # Create chat client for the agent
-    client = AzureOpenAIResponsesClient(
-        project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
-        deployment_name=os.environ["AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"],
+    client = FoundryChatClient(
+        project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
+        model=os.environ["FOUNDRY_MODEL"],
        credential=AzureCliCredential(),
    )
    # Create agent wired to the Redis context provider. The provider automatically
    # persists conversational details and surfaces relevant context on each turn.
-    agent = client.as_agent(
+    agent = Agent(
+        client=client,
        name="MemoryEnhancedAssistant",
        instructions=(
            "You are a helpful assistant. Personalize replies using provided context. "
@@ -29,15 +29,15 @@ Run:
 import asyncio
 import os

-from agent_framework.azure import AzureOpenAIResponsesClient
+from agent_framework import Agent
+from agent_framework.foundry import FoundryChatClient
 from agent_framework.redis import RedisContextProvider
 from azure.identity import AzureCliCredential
-from dotenv import load_dotenv
 from redisvl.extensions.cache.embeddings import EmbeddingsCache
 from redisvl.utils.vectorize import OpenAITextVectorizer

-# Load environment variables from .env file
-load_dotenv()
+# Copyright (c) Microsoft. All rights reserved.
+

 # Default Redis URL for local Redis Stack.
 # Override via the REDIS_URL environment variable for remote or authenticated instances.
@@ -45,12 +45,12 @@ REDIS_URL = os.getenv("REDIS_URL", "redis://localhost:6379")


 # Please set OPENAI_API_KEY to use the OpenAI vectorizer.
-# For chat responses, also set AZURE_AI_PROJECT_ENDPOINT and AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME.
-def create_chat_client() -> AzureOpenAIResponsesClient:
+# For chat responses, also set FOUNDRY_PROJECT_ENDPOINT and FOUNDRY_MODEL.
+def create_chat_client() -> FoundryChatClient:
    """Create an Azure OpenAI Responses client using a Foundry project endpoint."""
-    return AzureOpenAIResponsesClient(
-        project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
-        deployment_name=os.environ["AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"],
+    return FoundryChatClient(
+        project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
+        model=os.environ["FOUNDRY_MODEL"],
        credential=AzureCliCredential(),
    )

@@ -71,7 +71,8 @@ async def example_global_thread_scope() -> None:
        user_id="threads_demo_user",
    )

-    agent = client.as_agent(
+    agent = Agent(
+        client=client,
        name="GlobalMemoryAssistant",
        instructions=(
            "You are a helpful assistant. Personalize replies using provided context. "
@@ -128,7 +129,8 @@ async def example_per_operation_thread_scope() -> None:
        vector_distance_metric="cosine",
    )

-    agent = client.as_agent(
+    agent = Agent(
+        client=client,
        name="ScopedMemoryAssistant",
        instructions="You are an assistant with thread-scoped memory.",
        context_providers=[provider],
@@ -191,7 +193,8 @@ async def example_multiple_agents() -> None:
        vector_distance_metric="cosine",
    )

-    personal_agent = client.as_agent(
+    personal_agent = Agent(
+        client=client,
        name="PersonalAssistant",
        instructions="You are a personal assistant that helps with personal tasks.",
        context_providers=[personal_provider],
@@ -210,7 +213,8 @@ async def example_multiple_agents() -> None:
        vector_distance_metric="cosine",
    )

-    work_agent = client.as_agent(
+    work_agent = Agent(
+        client=client,
        name="WorkAssistant",
        instructions="You are a work assistant that helps with professional tasks.",
        context_providers=[work_provider],
@@ -6,7 +6,7 @@ from contextlib import suppress
 from typing import Any

 from agent_framework import Agent, AgentSession, BaseContextProvider, SessionContext, SupportsChatGetResponse
-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
@@ -89,9 +89,9 @@ class UserInfoMemory(BaseContextProvider):


 async def main():
-    client = AzureOpenAIResponsesClient(
-        project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
-        deployment_name=os.environ["AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"],
+    client = FoundryChatClient(
+        project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
+        model=os.environ["FOUNDRY_MODEL"],
        credential=AzureCliCredential(),
    )