Python: Refine samples and upgrade packages (#5261)

* Refine samples and upgrade pacakges * Upgrade to a new package that fixes a bug * Update model env var
2026-06-16 21:04:09 +08:00 · 2026-04-15 10:46:19 -07:00
parent 0402b1aac4
commit 383a2afca2
42 changed files with 285 additions and 517 deletions
@@ -0,0 +1,2 @@
+FOUNDRY_PROJECT_ENDPOINT="..."
+MODEL_DEPLOYMENT_NAME="..."
@@ -1,12 +1,6 @@
 # Basic example of hosting an agent with the `responses` API

-## Running the server locally
-
-Run the following command to start the server:
-
-```bash
-python main.py
-```
+This agent only contains an instruction (personal). It's the most basic agent with an LLM and no tools.

 ## Interacting with the agent

@@ -16,7 +10,11 @@ Send a POST request to the server with a JSON body containing a "message" field
 curl -X POST http://localhost:8088/responses -H "Content-Type: application/json" -d '{"input": "Hi"}'
 ```

-The server will respond with a JSON object containing the response text and a response ID. You can use this response ID to continue the conversation in subsequent requests.
+### Invoke with `azd`
+
+```bash
+azd ai agent invoke --local "Hi"
+```

 ## Multi-turn conversation

@@ -26,10 +24,10 @@ To have a multi-turn conversation with the agent, include the previous response
 curl -X POST http://localhost:8088/responses -H "Content-Type: application/json" -d '{"input": "How are you?", "previous_response_id": "REPLACE_WITH_PREVIOUS_RESPONSE_ID"}'
 ```

-## Deploying to Foundry
+Invoke with `azd`:

-TODO
+```bash
+azd ai agent invoke --local "Hi!" --conversation-id "my_conv"

-## Using the deployed agent in Agent Framework
-
-TODO
+azd ai agent invoke --local "How are you?" --conversation-id "my_conv"
+```
@@ -3,6 +3,7 @@ description: >
  A basic Agent Framework agent hosted by Foundry.
 metadata:
  tags:
+    - Agent Framework
    - AI Agent Hosting
    - Azure AI AgentServer
    - Responses Protocol
@@ -12,4 +13,11 @@ template:
  kind: hosted
  protocols:
    - protocol: responses
-      version: v0.1.0
+      version: 1.0.0
+  environment_variables:
+    - name: MODEL_DEPLOYMENT_NAME
+      value: "{{MODEL_DEPLOYMENT_NAME}}"
+resources:
+  - kind: model
+    id: gpt-4.1-mini
+    name: MODEL_DEPLOYMENT_NAME
@@ -16,7 +16,7 @@ load_dotenv()
 def main():
    client = FoundryChatClient(
        project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
-        model=os.environ["FOUNDRY_MODEL"],
+        model=os.environ["MODEL_DEPLOYMENT_NAME"],
        credential=AzureCliCredential(),
    )

@@ -0,0 +1,2 @@
+FOUNDRY_PROJECT_ENDPOINT="..."
+MODEL_DEPLOYMENT_NAME="..."
@@ -1,13 +1,23 @@
 # Basic example of hosting an agent with the `responses` API and local tools

-Run the following command to start the server:
+This agent is equipped with with a function tool and a local shell tool.

-```bash
-python main.py
-```
+> We recommend deploying this sample on a local container or to Foundry Hosting because the agent has access to a local shell tool, which can run arbitrary commands on the machine.
+
+## Interacting with the agent

 Send a POST request to the server with a JSON body containing a "message" field to interact with the agent. For example:

 ```bash
 curl -X POST http://localhost:8088/responses -H "Content-Type: application/json" -d '{"input": "What is the weather in Seattle?"}'
+
+curl -X POST http://localhost:8088/responses -H "Content-Type: application/json" -d '{"input": "List the files in the current directory."}'
+```
+
+Invoke with `azd`:
+
+```bash
+azd ai agent invoke --local "What is the weather in Seattle?"
+
+azd ai agent invoke --local "List the files in the current directory."
 ```
@@ -1,8 +1,9 @@
 name: agent-framework-agent-with-local-tools
 description: >
-  An Agent Framework agent with local toolshosted by Foundry.
+  An Agent Framework agent with local tools hosted by Foundry.
 metadata:
  tags:
+    - Agent Framework
    - AI Agent Hosting
    - Azure AI AgentServer
    - Responses Protocol
@@ -12,4 +13,11 @@ template:
  kind: hosted
  protocols:
    - protocol: responses
-      version: v0.1.0
+      version: 1.0.0
+  environment_variables:
+    - name: MODEL_DEPLOYMENT_NAME
+      value: "{{MODEL_DEPLOYMENT_NAME}}"
+resources:
+  - kind: model
+    id: gpt-4.1-mini
+    name: MODEL_DEPLOYMENT_NAME
@@ -1,6 +1,7 @@
 # Copyright (c) Microsoft. All rights reserved.

 import os
+import subprocess
 from random import randint

 from agent_framework import Agent, tool
@@ -25,17 +26,41 @@ def get_weather(
    return f"The weather in {location} is {conditions[randint(0, 3)]} with a high of {randint(10, 30)}°C."


+@tool(approval_mode="always_require")
+def run_bash(command: str) -> str:
+    """Execute a shell command locally and return stdout, stderr, and exit code."""
+    try:
+        result = subprocess.run(
+            command,
+            shell=True,
+            capture_output=True,
+            text=True,
+            timeout=30,
+        )
+        parts: list[str] = []
+        if result.stdout:
+            parts.append(result.stdout)
+        if result.stderr:
+            parts.append(f"stderr: {result.stderr}")
+        parts.append(f"exit_code: {result.returncode}")
+        return "\n".join(parts)
+    except subprocess.TimeoutExpired:
+        return "Command timed out after 30 seconds"
+    except Exception as e:
+        return f"Error executing command: {e}"
+
+
 def main():
    client = FoundryChatClient(
        project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
-        model=os.environ["FOUNDRY_MODEL"],
+        model=os.environ["MODEL_DEPLOYMENT_NAME"],
        credential=AzureCliCredential(),
    )

    agent = Agent(
        client=client,
        instructions="You are a friendly assistant. Keep your answers brief.",
-        tools=[get_weather],
+        tools=[get_weather, run_bash],
        # History will be managed by the hosting infrastructure, thus there
        # is no need to store history by the service. Learn more at:
        # https://developers.openai.com/api/reference/resources/responses/methods/create
@@ -0,0 +1,4 @@
+FOUNDRY_PROJECT_ENDPOINT="..."
+MODEL_DEPLOYMENT_NAME="..."
+FOUNDRY_AGENT_TOOLBOX_NAME="..."
+GITHUB_PAT="..."
@@ -1,13 +1,19 @@
 # Basic example of hosting an agent with the `responses` API and a remote MCP

-Run the following command to start the server:
+This agent is equipped with a GitHub MCP server and a Foundry Toolbox, which are both remote MCPs.

-```bash
-python main.py
-```
+> Note that there are other ways to interact with Foundry toolboxes. Using it as a MCP is just one of the options.
+
+## Interacting with the agent

 Send a POST request to the server with a JSON body containing a "message" field to interact with the agent. For example:

 ```bash
 curl -X POST http://localhost:8088/responses -H "Content-Type: application/json" -d '{"input": "List all the repositories I own on GitHub."}'
 ```
+
+Invoke with `azd`:
+
+```bash
+azd ai agent invoke --local "List all the repositories I own on GitHub."
+```
@@ -3,6 +3,7 @@ description: >
  An Agent Framework agent with remote MCP tools hosted by Foundry.
 metadata:
  tags:
+    - Agent Framework
    - AI Agent Hosting
    - Azure AI AgentServer
    - Responses Protocol
@@ -12,4 +13,15 @@ template:
  kind: hosted
  protocols:
    - protocol: responses
-      version: v0.1.0
+      version: 1.0.0
+  environment_variables:
+    - name: MODEL_DEPLOYMENT_NAME
+      value: "{{MODEL_DEPLOYMENT_NAME}}"
+    - name: GITHUB_PAT
+      value: ${GITHUB_PAT}
+    - name: FOUNDRY_AGENT_TOOLBOX_NAME
+      value: ${FOUNDRY_AGENT_TOOLBOX_NAME}
+resources:
+  - kind: model
+    id: gpt-4.1-mini
+    name: MODEL_DEPLOYMENT_NAME
@@ -2,7 +2,8 @@

 import os

-from agent_framework import Agent
+import httpx
+from agent_framework import Agent, MCPStreamableHTTPTool
 from agent_framework.foundry import FoundryChatClient
 from agent_framework_foundry_hosting import ResponsesHostServer
 from azure.ai.agentserver.responses import InMemoryResponseProvider
@@ -13,14 +14,37 @@ from dotenv import load_dotenv
 load_dotenv()


+class ToolboxAuth(httpx.Auth):
+    """httpx Auth that injects a fresh bearer token on every request."""
+
+    def auth_flow(self, request: httpx.Request):
+        credential = AzureCliCredential()
+        token = credential.get_token("https://ai.azure.com/.default").token
+        request.headers["Authorization"] = f"Bearer {token}"
+        yield request
+
+
 def main():
    client = FoundryChatClient(
        project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
-        model=os.environ["FOUNDRY_MODEL"],
+        model=os.environ["MODEL_DEPLOYMENT_NAME"],
        credential=AzureCliCredential(),
    )

-    github_pat = os.getenv("GITHUB_PAT")
+    # Foundry Toolbox as a MCP tool
+    project_endpoint = os.environ["FOUNDRY_PROJECT_ENDPOINT"]
+    toolbox_name = os.environ["FOUNDRY_AGENT_TOOLBOX_NAME"]
+    toolbox_endpoint = f"{project_endpoint.rstrip('/')}/toolboxes/{toolbox_name}/mcp?api-version=v1"
+    http_client = httpx.AsyncClient(auth=ToolboxAuth(), headers={"Foundry-Features": "Toolboxes=V1Preview"})
+    foundry_mcp_tool = MCPStreamableHTTPTool(
+        name="toolbox",
+        url=toolbox_endpoint,
+        http_client=http_client,
+        load_prompts=False,
+    )
+
+    # GitHub MCP server
+    github_pat = os.environ["GITHUB_PAT"]
    if not github_pat:
        raise ValueError(
            "GITHUB_PAT environment variable must be set. Create a token at https://github.com/settings/tokens"
@@ -38,7 +62,7 @@ def main():
    agent = Agent(
        client=client,
        instructions="You are a friendly assistant. Keep your answers brief.",
-        tools=[github_mcp_tool],
+        tools=[foundry_mcp_tool, github_mcp_tool],
        # History will be managed by the hosting infrastructure, thus there
        # is no need to store history by the service. Learn more at:
        # https://developers.openai.com/api/reference/resources/responses/methods/create
@@ -0,0 +1,2 @@
+FOUNDRY_PROJECT_ENDPOINT="..."
+MODEL_DEPLOYMENT_NAME="..."
@@ -1,13 +1,17 @@
 # Basic example of hosting an agent with the `responses` API and a workflow

-Run the following command to start the server:
+This sample demonstrates how to host a workflow using the `responses` API.

-```bash
-python main.py
-```
+## Interacting with the agent

 Send a POST request to the server with a JSON body containing a "message" field to interact with the agent. For example:

 ```bash
 curl -X POST http://localhost:8088/responses -H "Content-Type: application/json" -d '{"input": "Create a slogan for a new electric SUV that is affordable and fun to drive."}'
 ```
+
+Invoke with `azd`:
+
+```bash
+azd ai agent invoke --local "List all the repositories I own on GitHub."
+```
@@ -3,6 +3,7 @@ description: >
  An Agent Framework workflow hosted by Foundry.
 metadata:
  tags:
+    - Agent Framework
    - AI Agent Hosting
    - Azure AI AgentServer
    - Responses Protocol
@@ -12,4 +13,11 @@ template:
  kind: hosted
  protocols:
    - protocol: responses
-      version: v0.1.0
+      version: 1.0.0
+  environment_variables:
+    - name: MODEL_DEPLOYMENT_NAME
+      value: "{{MODEL_DEPLOYMENT_NAME}}"
+resources:
+  - kind: model
+    id: gpt-4.1-mini
+    name: MODEL_DEPLOYMENT_NAME
@@ -24,7 +24,7 @@ def round_robin_selector(state: GroupChatState) -> str:
 def main():
    client = FoundryChatClient(
        project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
-        model=os.environ["FOUNDRY_MODEL"],
+        model=os.environ["MODEL_DEPLOYMENT_NAME"],
        credential=AzureCliCredential(),
    )

@@ -1,6 +0,0 @@
-.venv
-__pycache__
-*.pyc
-*.pyo
-*.pyd
-.Python
@@ -1,16 +0,0 @@
-FROM python:3.12-slim
-
-WORKDIR /app/user_agent
-
-COPY wheels/ /tmp/wheels/
-COPY requirements.txt .
-RUN pip install --no-cache-dir --find-links /tmp/wheels/ -r requirements.txt && rm -rf /tmp/wheels/
-
-COPY . .
-
-RUN useradd -r appuser
-USER appuser
-
-EXPOSE 8088
-
-CMD ["python", "main.py"]
@@ -1,43 +0,0 @@
-# Agent Framework Agent with Local Shell
-
-> Note: This agent can execute local shell commands. We recommend running it in an isolated environment for security reasons.
-
-## Running the server in a Docker container
-
-Build the Docker image:
-
-```bash
-docker build -t agent-framework-agent-with-local-shell .
-```
-
-Run the Docker container:
-
-```bash
-docker run -p 8088:8088 --env-file .env agent-framework-agent-with-local-shell
-```
-
-## Interacting with the agent
-
-Send a POST request to the server with a JSON body containing a "message" field to interact with the agent. For example:
-
-```bash
-curl -X POST http://localhost:8088/responses -H "Content-Type: application/json" -d '{"input": "Hi"}'
-```
-
-The server will respond with a JSON object containing the response text and a response ID. You can use this response ID to continue the conversation in subsequent requests.
-
-## Multi-turn conversation
-
-To have a multi-turn conversation with the agent, include the previous response id in the request body. For example:
-
-```bash
-curl -X POST http://localhost:8088/responses -H "Content-Type: application/json" -d '{"input": "How are you?", "previous_response_id": "REPLACE_WITH_PREVIOUS_RESPONSE_ID"}'
-```
-
-## Deploying to Foundry
-
-TODO
-
-## Using the deployed agent in Agent Framework
-
-TODO
@@ -1,15 +0,0 @@
-name: agent-framework-agent-with-local-shell
-description: >
-  An Agent Framework agent that can execute local shell commands hosted by Foundry.
-metadata:
-  tags:
-    - AI Agent Hosting
-    - Azure AI AgentServer
-    - Responses Protocol
-    - Streaming
-template:
-  name: agent-framework-agent-with-local-shell
-  kind: hosted
-  protocols:
-    - protocol: responses
-      version: v0.1.0
@@ -1,8 +0,0 @@
-kind: hosted
-name: agent-framework-agent-with-local-shell
-protocols:
-  - protocol: responses
-    version: v0.1.0
-resources:
-  cpu: "0.25"
-  memory: 0.5Gi
@@ -1,63 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-import os
-import subprocess
-
-from agent_framework import Agent, tool
-from agent_framework.foundry import FoundryChatClient
-from agent_framework_foundry_hosting import ResponsesHostServer
-from azure.ai.agentserver.responses import InMemoryResponseProvider
-from azure.identity import AzureCliCredential
-from dotenv import load_dotenv
-
-# Load environment variables from .env file
-load_dotenv()
-
-
-@tool(approval_mode="always_require")
-def run_bash(command: str) -> str:
-    """Execute a shell command locally and return stdout, stderr, and exit code."""
-    try:
-        result = subprocess.run(
-            command,
-            shell=True,
-            capture_output=True,
-            text=True,
-            timeout=30,
-        )
-        parts: list[str] = []
-        if result.stdout:
-            parts.append(result.stdout)
-        if result.stderr:
-            parts.append(f"stderr: {result.stderr}")
-        parts.append(f"exit_code: {result.returncode}")
-        return "\n".join(parts)
-    except subprocess.TimeoutExpired:
-        return "Command timed out after 30 seconds"
-    except Exception as e:
-        return f"Error executing command: {e}"
-
-
-def main():
-    client = FoundryChatClient(
-        project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
-        model=os.environ["FOUNDRY_MODEL"],
-        credential=AzureCliCredential(),
-    )
-
-    agent = Agent(
-        client=client,
-        instructions="You are a friendly assistant. Keep your answers brief.",
-        tools=[run_bash],
-        # History will be managed by the hosting infrastructure, thus there
-        # is no need to store history by the service. Learn more at:
-        # https://developers.openai.com/api/reference/resources/responses/methods/create
-        default_options={"store": False},
-    )
-
-    server = ResponsesHostServer(agent, store=InMemoryResponseProvider())
-    server.run()
-
-
-if __name__ == "__main__":
-    main()
@@ -1,2 +0,0 @@
-agent-framework-core
-agent-framework-foundry-hosting
@@ -1,6 +0,0 @@
-.venv
-__pycache__
-*.pyc
-*.pyo
-*.pyd
-.Python
@@ -1,16 +0,0 @@
-FROM python:3.12-slim
-
-WORKDIR /app
-
-COPY . user_agent/
-WORKDIR /app/user_agent
-
-RUN if [ -f requirements.txt ]; then \
-        pip install -r requirements.txt; \
-    else \
-        echo "No requirements.txt found"; \
-    fi
-
-EXPOSE 8088
-
-CMD ["python", "main.py"]
@@ -1,35 +0,0 @@
-# Agent Framework Agent with Evaluation
-
-## Running the server locally
-
-Run the following command to start the server:
-
-```bash
-python main.py
-```
-
-## Interacting with the agent
-
-Send a POST request to the server with a JSON body containing a "message" field to interact with the agent. For example:
-
-```bash
-curl -X POST http://localhost:8088/responses -H "Content-Type: application/json" -d '{"input": "Hi"}'
-```
-
-The server will respond with a JSON object containing the response text and a response ID. You can use this response ID to continue the conversation in subsequent requests.
-
-## Multi-turn conversation
-
-To have a multi-turn conversation with the agent, include the previous response id in the request body. For example:
-
-```bash
-curl -X POST http://localhost:8088/responses -H "Content-Type: application/json" -d '{"input": "How are you?", "previous_response_id": "REPLACE_WITH_PREVIOUS_RESPONSE_ID"}'
-```
-
-## Deploying to Foundry
-
-TODO
-
-## Using the deployed agent in Agent Framework
-
-TODO
@@ -1,15 +0,0 @@
-name: agent-framework-agent-with-eval
-description: >
-  An Agent Framework agent is evaluated on each response hosted by Foundry.
-metadata:
-  tags:
-    - AI Agent Hosting
-    - Azure AI AgentServer
-    - Responses Protocol
-    - Streaming
-template:
-  name: agent-framework-agent-with-eval
-  kind: hosted
-  protocols:
-    - protocol: responses
-      version: v0.1.0
@@ -1,8 +0,0 @@
-kind: hosted
-name: agent-framework-agent-with-eval
-protocols:
-  - protocol: responses
-    version: v0.1.0
-resources:
-  cpu: "0.25"
-  memory: 0.5Gi
@@ -1,50 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-import os
-from random import randint
-
-from agent_framework import Agent, tool
-from agent_framework.foundry import FoundryChatClient
-from agent_framework_foundry_hosting import ResponsesHostServer
-from azure.ai.agentserver.responses import InMemoryResponseProvider
-from azure.identity import AzureCliCredential
-from dotenv import load_dotenv
-from pydantic import Field
-from typing_extensions import Annotated
-
-# Load environment variables from .env file
-load_dotenv()
-
-
-@tool(approval_mode="never_require")
-def get_weather(
-    location: Annotated[str, Field(description="The location to get the weather for.")],
-) -> str:
-    """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."
-
-
-def main():
-    client = FoundryChatClient(
-        project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
-        model=os.environ["FOUNDRY_MODEL"],
-        credential=AzureCliCredential(),
-    )
-
-    agent = Agent(
-        client=client,
-        instructions="You are a friendly assistant. Keep your answers brief.",
-        tools=[get_weather],
-        # History will be managed by the hosting infrastructure, thus there
-        # is no need to store history by the service. Learn more at:
-        # https://developers.openai.com/api/reference/resources/responses/methods/create
-        default_options={"store": False},
-    )
-
-    server = ResponsesHostServer(agent, store=InMemoryResponseProvider())
-    server.run()
-
-
-if __name__ == "__main__":
-    main()
@@ -1,2 +0,0 @@
-agent-framework
-agent-framework-foundry-hosting
@@ -1,6 +0,0 @@
-.venv
-__pycache__
-*.pyc
-*.pyo
-*.pyd
-.Python
@@ -1,16 +0,0 @@
-FROM python:3.12-slim
-
-WORKDIR /app
-
-COPY . user_agent/
-WORKDIR /app/user_agent
-
-RUN if [ -f requirements.txt ]; then \
-        pip install -r requirements.txt; \
-    else \
-        echo "No requirements.txt found"; \
-    fi
-
-EXPOSE 8088
-
-CMD ["python", "main.py"]
@@ -1,35 +0,0 @@
-# Agent Framework Agent with Foundry Memory
-
-## Running the server locally
-
-Run the following command to start the server:
-
-```bash
-python main.py
-```
-
-## Interacting with the agent
-
-Send a POST request to the server with a JSON body containing a "message" field to interact with the agent. For example:
-
-```bash
-curl -X POST http://localhost:8088/responses -H "Content-Type: application/json" -d '{"input": "Hi"}'
-```
-
-The server will respond with a JSON object containing the response text and a response ID. You can use this response ID to continue the conversation in subsequent requests.
-
-## Multi-turn conversation
-
-To have a multi-turn conversation with the agent, include the previous response id in the request body. For example:
-
-```bash
-curl -X POST http://localhost:8088/responses -H "Content-Type: application/json" -d '{"input": "How are you?", "previous_response_id": "REPLACE_WITH_PREVIOUS_RESPONSE_ID"}'
-```
-
-## Deploying to Foundry
-
-TODO
-
-## Using the deployed agent in Agent Framework
-
-TODO
@@ -1,15 +0,0 @@
-name: agent-framework-agent-with-foundry-memory
-description: >
-  An Agent Framework agent with memory support hosted by Foundry.
-metadata:
-  tags:
-    - AI Agent Hosting
-    - Azure AI AgentServer
-    - Responses Protocol
-    - Streaming
-template:
-  name: agent-framework-agent-with-foundry-memory
-  kind: hosted
-  protocols:
-    - protocol: responses
-      version: v0.1.0
@@ -1,8 +0,0 @@
-kind: hosted
-name: agent-framework-agent-with-foundry-memory
-protocols:
-  - protocol: responses
-    version: v0.1.0
-resources:
-  cpu: "0.25"
-  memory: 0.5Gi
@@ -1,91 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-import asyncio
-import logging
-import os
-from datetime import datetime, timezone
-
-from agent_framework import Agent
-from agent_framework.foundry import FoundryChatClient, FoundryMemoryProvider
-from agent_framework_foundry_hosting import ResponsesHostServer
-from azure.ai.agentserver.responses import InMemoryResponseProvider
-from azure.ai.projects.aio import AIProjectClient
-from azure.ai.projects.models import (
-    MemoryStoreDefaultDefinition,
-    MemoryStoreDefaultOptions,
-)
-from azure.identity import AzureCliCredential
-from dotenv import load_dotenv
-
-# Load environment variables from .env file
-load_dotenv()
-
-logging.basicConfig(level=logging.INFO)
-
-
-async def _create_memory_store(project_client: AIProjectClient) -> FoundryMemoryProvider:
-    memory_store_name = f"hosted_agent_memory_{datetime.now(timezone.utc).strftime('%Y%m%d')}"
-    options = MemoryStoreDefaultOptions(
-        chat_summary_enabled=True,
-        user_profile_enabled=True,
-        user_profile_details=(
-            "Avoid irrelevant or sensitive data, such as age, financials, precise location, and credentials"
-        ),
-    )
-    memory_store_definition = MemoryStoreDefaultDefinition(
-        chat_model=os.environ["FOUNDRY_MODEL"],
-        embedding_model=os.environ["AZURE_OPENAI_EMBEDDING_MODEL"],
-        options=options,
-    )
-    memory_store = await project_client.beta.memory_stores.create(
-        name=memory_store_name,
-        description="Memory store for Agent Framework with FoundryMemoryProvider",
-        definition=memory_store_definition,
-    )
-
-    return FoundryMemoryProvider(
-        project_client=project_client,
-        memory_store_name=memory_store.name,
-        # Scope memories to a specific user, if not set, the session_id
-        # will be used as scope, which means memories are only shared within the same session
-        scope="demo",
-        # Do not wait to update memories after each interaction (for demo purposes)
-        # In production, consider setting a delay to batch updates and reduce costs
-        update_delay=0,
-    )
-
-
-async def _delete_memory_store(project_client: AIProjectClient, memory_store_name: str):
-    await project_client.beta.memory_stores.delete(name=memory_store_name)
-
-
-async def main():
-    client = FoundryChatClient(
-        project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
-        model=os.environ["FOUNDRY_MODEL"],
-        credential=AzureCliCredential(),
-    )
-
-    # Create the memory store
-    memory_provider = await _create_memory_store(client.project_client)
-
-    agent = Agent(
-        client=client,
-        instructions="You are a friendly assistant. Keep your answers brief.",
-        context_providers=[memory_provider],
-        # History will be managed by the hosting infrastructure, thus there
-        # is no need to store history by the service. Learn more at:
-        # https://developers.openai.com/api/reference/resources/responses/methods/create
-        default_options={"store": False},
-    )
-
-    server = ResponsesHostServer(agent, store=InMemoryResponseProvider())
-
-    try:
-        await server.run_async()
-    finally:
-        await _delete_memory_store(client.project_client, memory_provider.memory_store_name)
-
-
-if __name__ == "__main__":
-    asyncio.run(main())
@@ -1,2 +0,0 @@
-agent-framework
-agent-framework-foundry-hosting
@@ -0,0 +1,65 @@
+# Hosting agents with Foundry Hosting and the `responses` API
+
+This folder contains a list of samples that show how to host agents using the `responses` API and deploy them to Foundry Hosting.
+
+| Sample | Description |
+| --- | --- |
+| [01_basic](./01_basic) | A basic example of hosting an agent with the `responses` API and carrying on a multi-turn conversation. |
+| [02_local_tools](./02_local_tools) | An example of hosting an agent with the `responses` API and local tools including a function tool and a local shell tool. |
+| [03_remote_mcp](./03_remote_mcp) | An example of hosting an agent with the `responses` API and remote MCPs, including a GitHub MCP server and a Foundry Toolboox. |
+| [04_workflows](./04_workflows) | An example of hosting a workflow with the `responses` API. |
+
+## Running the server locally
+
+Navigate to the sample directory and run the following command to start the server:
+
+```bash
+python main.py
+```
+
+## Interacting with the agent
+
+There two ways to interact with the agent: sending HTTP requests to the server or using the `azd` CLI:
+
+### Invoke with `azd`
+
+```bash
+azd ai agent invoke --local "Hi"
+```
+
+### Sending HTTP requests
+
+Send a POST request to the server with a JSON body containing a "message" field to interact with the agent. For example:
+
+```bash
+curl -X POST http://localhost:8088/responses -H "Content-Type: application/json" -d '{"input": "Hi"}'
+```
+
+> See the individual samples for more examples of interacting with the agent.
+
+## Deploying to a Docker container
+
+Navigate to the sample directory and build the Docker image:
+
+```bash
+docker build -t hosted-agent-sample .
+```
+
+Run the container, passing in the required environment variables:
+
+```bash
+docker run -p 8088:8088 \
+  -e FOUNDRY_PROJECT_ENDPOINT=<your-endpoint> \
+  -e FOUNDRY_MODEL=<your-model> \
+  hosted-agent-sample
+```
+
+The server will be available at `http://localhost:8088`. You can send requests using the same `curl` command shown above.
+
+## Deploying to Foundry
+
+TODO
+
+## Using the deployed agent in Agent Framework
+
+After deploying the agent, you can also try to use the agent in Agent Framework. Refer to the [using_deployed_agent.py](./using_deployed_agent.py) sample for an example of how to do this.
@@ -0,0 +1,50 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+import asyncio
+
+from agent_framework import Agent, AgentResponse, AgentResponseUpdate, ResponseStream
+from agent_framework.openai import OpenAIChatClient
+from typing_extensions import Any
+
+"""
+This script demonstrates how to talk to a deployed agent using the OpenAIChatClient.
+
+Depending on where you have deployed your agent (local or Foundry Hosting), you may
+need to change the base_url when initializing the OpenAIChatClient.
+"""
+
+
+async def print_streaming_response(streaming_response: ResponseStream[AgentResponseUpdate, AgentResponse[Any]]) -> None:
+    async for chunk in streaming_response:
+        if chunk.text:
+            print(chunk.text, end="", flush=True)
+
+
+async def main() -> None:
+    agent = Agent(client=OpenAIChatClient(base_url="http://localhost:8088"))
+    session = agent.create_session()
+
+    # First turn
+    query = "Hi!"
+    print(f"User: {query}")
+    print("Agent: ", end="", flush=True)
+    streaming_response = agent.run(query, session=session, stream=True)
+    await print_streaming_response(streaming_response)
+
+    # Second turn
+    query = "You name is Javis. What can you do?"
+    print(f"\nUser: {query}")
+    print("Agent: ", end="", flush=True)
+    streaming_response = agent.run(query, session=session, stream=True)
+    await print_streaming_response(streaming_response)
+
+    # Third turn
+    query = "What is your name?"
+    print(f"\nUser: {query}")
+    print("Agent: ", end="", flush=True)
+    streaming_response = agent.run(query, session=session, stream=True)
+    await print_streaming_response(streaming_response)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())