Update foundry hosting samples

2026-06-16 21:04:09 +08:00 · 2026-04-24 11:48:17 -07:00
parent 0b69d7fd15
commit 334ce4dfe0
55 changed files with 653 additions and 259 deletions
@@ -1,2 +1,2 @@
 FOUNDRY_PROJECT_ENDPOINT="..."
-MODEL_DEPLOYMENT_NAME="..."
+AZURE_AI_MODEL_DEPLOYMENT_NAME="..."
@@ -1,18 +1,26 @@
-# Basic example of hosting an agent with the `invocations` API
+# What this sample demonstrates

-## Running the server locally
+An [Agent Framework](https://github.com/microsoft/agent-framework) agent hosted using the **Invocations protocol** with session management. Unlike the Responses protocol, the Invocations protocol does **not** provide built-in server-side conversation history — this agent maintains an in-memory session store keyed by `agent_session_id`. In production, replace it with durable storage (Redis, Cosmos DB, etc.) so history survives restarts.

-### Environment setup
+## How It Works

-Follow the instructions in the [Environment setup](../../README.md#environment-setup) section of the README in the parent directory to set up your environment and install dependencies.
+### Model Integration

-Run the following command to start the server:
+The agent uses `FoundryChatClient` from the Agent Framework to create a Responses client from the project endpoint and model deployment. When a request arrives, the handler looks up (or creates) a session by `session_id`, runs the agent with the user message and session context, and returns the reply. The agent supports both streaming (SSE events) and non-streaming (JSON) response modes.

-```bash
-python main.py
-```
+See [main.py](main.py) for the full implementation.

-### Interacting with the agent
+### Agent Hosting
+
+The agent is hosted using the [Agent Framework](https://github.com/microsoft/agent-framework) with the `InvocationsHostServer`, which provisions a REST API endpoint compatible with the Azure AI Invocations protocol.
+
+## Running the Agent Host
+
+Follow the instructions in the [Running the Agent Host Locally](../../README.md#running-the-agent-host-locally) section of the README in the parent directory to run the agent host.
+
+## Interacting with the agent
+
+> Depending on how you run the agent host, you can invoke the agent using `curl` (`Invoke-WebRequest` in PowerShell) or `azd`. Please refer to the [parent README](../../README.md) for more details. Use this README for sample queries you can send to the agent.

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

@@ -22,7 +30,7 @@ curl -X POST http://localhost:8088/invocations -i -H "Content-Type: application/

 The server will respond with a JSON object containing the response text. The `-i` flag in the `curl` command includes the HTTP response headers in the output, which includes the session ID that can be used for multi-turn conversations. Here is an example of the response:

-```bash
+```
 HTTP/1.1 200
 content-length: 34
 content-type: application/json
@@ -42,3 +50,7 @@ To have a multi-turn conversation with the agent, take the session ID from the r
 ```bash
 curl -X POST http://localhost:8088/invocations?agent_session_id=9370b9d4-cd13-4436-a57f-03b843ac0e17 -i -H "Content-Type: application/json" -d '{"message": "How are you?"}'
 ```
+
+## Deploying the Agent to Foundry
+
+To host the agent on Foundry, follow the instructions in the [Deploying the Agent to Foundry](../../README.md#deploying-the-agent-to-foundry) section of the README in the parent directory.
@@ -15,9 +15,9 @@ template:
    - protocol: invocations
      version: 1.0.0
  environment_variables:
-    - name: MODEL_DEPLOYMENT_NAME
-      value: "{{MODEL_DEPLOYMENT_NAME}}"
+    - name: AZURE_AI_MODEL_DEPLOYMENT_NAME
+      value: "{{AZURE_AI_MODEL_DEPLOYMENT_NAME}}"
 resources:
  - kind: model
    id: gpt-4.1-mini
-    name: MODEL_DEPLOYMENT_NAME
+    name: AZURE_AI_MODEL_DEPLOYMENT_NAME
@@ -6,4 +6,4 @@ protocols:
    version: 1.0.0
 resources:
  cpu: '0.25'
-  memory: '0.5Gi'
+  memory: '0.5Gi'
@@ -5,7 +5,7 @@ import os
 from agent_framework import Agent
 from agent_framework.foundry import FoundryChatClient
 from agent_framework_foundry_hosting import InvocationsHostServer
-from azure.identity import AzureCliCredential
+from azure.identity import DefaultAzureCredential
 from dotenv import load_dotenv

 # Load environment variables from .env file
@@ -15,8 +15,8 @@ load_dotenv()
 def main():
    client = FoundryChatClient(
        project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
-        model=os.environ["MODEL_DEPLOYMENT_NAME"],
-        credential=AzureCliCredential(),
+        model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
+        credential=DefaultAzureCredential(),
    )

    agent = Agent(
@@ -1,2 +1,2 @@
 FOUNDRY_PROJECT_ENDPOINT="..."
-MODEL_DEPLOYMENT_NAME="..."
+AZURE_AI_MODEL_DEPLOYMENT_NAME="..."
@@ -1,20 +1,26 @@
-# Basic example of hosting an agent with the `invocations` API
+# What this sample demonstrates

-This is the same as the [01_basic](../01_basic/README.md) example, but demonstrates the "break glass" scenario where you can create your own `invoke_handler` to handle specific types of invocations. This is useful when you want to override the default behavior for certain requests or add custom processing logic.
+An [Agent Framework](https://github.com/microsoft/agent-framework) agent hosted using the **Invocations protocol** with session management. Unlike the Responses protocol, the Invocations protocol does **not** provide built-in server-side conversation history — this agent maintains an in-memory session store keyed by `agent_session_id`. In production, replace it with durable storage (Redis, Cosmos DB, etc.) so history survives restarts.

-## Running the server locally
+## How It Works

-### Environment setup
+### Model Integration

-Follow the instructions in the [Environment setup](../../README.md#environment-setup) section of the README in the parent directory to set up your environment and install dependencies.
+The agent uses `FoundryChatClient` from the Agent Framework to create a Responses client from the project endpoint and model deployment. When a request arrives, the handler looks up (or creates) a session by `session_id`, runs the agent with the user message and session context, and returns the reply. The agent supports both streaming (SSE events) and non-streaming (JSON) response modes.

-Run the following command to start the server:
+See [main.py](main.py) for the full implementation.

-```bash
-python main.py
-```
+### Agent Hosting

-### Interacting with the agent
+The agent is hosted using the [Azure AI AgentServer Invocations SDK](https://pypi.org/project/azure-ai-agentserver-invocations/) (`InvocationAgentServerHost`), which provisions a REST API endpoint compatible with the Azure AI Invocations protocol.
+
+## Running the Agent Host
+
+Follow the instructions in the [Running the Agent Host Locally](../../README.md#running-the-agent-host-locally) section of the README in the parent directory to run the agent host.
+
+## Interacting with the agent
+
+> Depending on how you run the agent host, you can invoke the agent using `curl` (`Invoke-WebRequest` in PowerShell) or `azd`. Please refer to the [parent README](../../README.md) for more details. Use this README for sample queries you can send to the agent.

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

@@ -24,7 +30,7 @@ curl -X POST http://localhost:8088/invocations -i -H "Content-Type: application/

 The server will respond with a JSON object containing the response text. The `-i` flag in the `curl` command includes the HTTP response headers in the output, which includes the session ID that can be used for multi-turn conversations. Here is an example of the response:

-```bash
+```
 HTTP/1.1 200
 content-length: 34
 content-type: application/json
@@ -44,3 +50,7 @@ To have a multi-turn conversation with the agent, take the session ID from the r
 ```bash
 curl -X POST http://localhost:8088/invocations?agent_session_id=9370b9d4-cd13-4436-a57f-03b843ac0e17 -i -H "Content-Type: application/json" -d '{"message": "How are you?"}'
 ```
+
+## Deploying the Agent to Foundry
+
+To host the agent on Foundry, follow the instructions in the [Deploying the Agent to Foundry](../../README.md#deploying-the-agent-to-foundry) section of the README in the parent directory.
@@ -15,9 +15,9 @@ template:
    - protocol: invocations
      version: 1.0.0
  environment_variables:
-    - name: MODEL_DEPLOYMENT_NAME
-      value: "{{MODEL_DEPLOYMENT_NAME}}"
+    - name: AZURE_AI_MODEL_DEPLOYMENT_NAME
+      value: "{{AZURE_AI_MODEL_DEPLOYMENT_NAME}}"
 resources:
  - kind: model
    id: gpt-4.1-mini
-    name: MODEL_DEPLOYMENT_NAME
+    name: AZURE_AI_MODEL_DEPLOYMENT_NAME
@@ -6,4 +6,4 @@ protocols:
    version: 1.0.0
 resources:
  cpu: '0.25'
-  memory: '0.5Gi'
+  memory: '0.5Gi'
@@ -22,7 +22,7 @@ _sessions: dict[str, AgentSession] = {}
 # Create the agent
 client = FoundryChatClient(
    project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
-    model=os.environ["MODEL_DEPLOYMENT_NAME"],
+    model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
    credential=DefaultAzureCredential(),
 )

@@ -1,8 +0,0 @@
-# Hosting agents with Foundry Hosting and the `invocations` API
-
-This folder contains a list of samples that show how to host agents using the `invocations` API and deploy them to Foundry Hosting.
-
-| Sample | Description |
-| --- | --- |
-| [01_basic](./01_basic) | A basic example of hosting an agent with the `invocations` API and carrying on a multi-turn conversation. |
-| [02_break_glass](./02_break_glass) | An example of hosting an agent with the `invocations` API and a "break glass" scenario where you can create your own `invoke_handler` to handle specific types of invocations. |
@@ -1,2 +1,2 @@
 FOUNDRY_PROJECT_ENDPOINT="..."
-MODEL_DEPLOYMENT_NAME="..."
+AZURE_AI_MODEL_DEPLOYMENT_NAME="..."
@@ -1,31 +1,39 @@
-# Basic example of hosting an agent with the `responses` API
+# What this sample demonstrates

-This agent only contains an instruction (personal). It's the most basic agent with an LLM and no tools.
+An [Agent Framework](https://github.com/microsoft/agent-framework) agent hosted using the **Responses protocol**.

-## Running the server locally
+## How It Works

-### Environment setup
+### Model Integration

-Follow the instructions in the [Environment setup](../../README.md#environment-setup) section of the README in the parent directory to set up your environment and install dependencies.
+The agent uses `FoundryChatClient` from the Agent Framework to create a Responses client from the project endpoint and model deployment. The agent supports both streaming (SSE events) and non-streaming (JSON) response modes.

-Run the following command to start the server:
+See [main.py](main.py) for the full implementation.

-```bash
-python main.py
-```
+### Agent Hosting
+
+The agent is hosted using the [Agent Framework](https://github.com/microsoft/agent-framework) with the `ResponsesHostServer`, which provisions a REST API endpoint compatible with the OpenAI Responses protocol.

 ## Interacting with the agent

-Send a POST request to the server with a JSON body containing a "input" field to interact with the agent. For example:
+> Depending on how you run the agent host, you can invoke the agent using `curl` (`Invoke-WebRequest` in PowerShell) or `azd`. Please refer to the [parent README](../../README.md) for more details. Use this README for sample queries you can send to 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"}'
 ```

-## Multi-turn conversation
+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 the Agent to Foundry
+
+To host the agent on Foundry, follow the instructions in the [Deploying the Agent to Foundry](../../README.md#deploying-the-agent-to-foundry) section of the README in the parent directory.
@@ -1,4 +1,4 @@
-name: agent-framework-agent-basic
+name: agent-framework-agent-basic-responses
 description: >
  A basic Agent Framework agent hosted by Foundry.
 metadata:
@@ -9,15 +9,15 @@ metadata:
    - Responses Protocol
    - Streaming
 template:
-  name: agent-framework-agent-basic
+  name: agent-framework-agent-basic-responses
  kind: hosted
  protocols:
    - protocol: responses
      version: 1.0.0
  environment_variables:
-    - name: MODEL_DEPLOYMENT_NAME
-      value: "{{MODEL_DEPLOYMENT_NAME}}"
+    - name: AZURE_AI_MODEL_DEPLOYMENT_NAME
+      value: "{{AZURE_AI_MODEL_DEPLOYMENT_NAME}}"
 resources:
  - kind: model
    id: gpt-4.1-mini
-    name: MODEL_DEPLOYMENT_NAME
+    name: AZURE_AI_MODEL_DEPLOYMENT_NAME
@@ -1,8 +1,9 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/microsoft/AgentSchema/refs/heads/main/schemas/v1.0/ContainerAgent.yaml
 kind: hosted
-name: agent-framework-agent-basic
+name: agent-framework-agent-basic-responses
 protocols:
  - protocol: responses
    version: 1.0.0
 resources:
-  cpu: "0.25"
-  memory: 0.5Gi
+  cpu: '0.25'
+  memory: '0.5Gi'
@@ -5,7 +5,7 @@ import os
 from agent_framework import Agent
 from agent_framework.foundry import FoundryChatClient
 from agent_framework_foundry_hosting import ResponsesHostServer
-from azure.identity import AzureCliCredential
+from azure.identity import DefaultAzureCredential
 from dotenv import load_dotenv

 # Load environment variables from .env file
@@ -15,8 +15,8 @@ load_dotenv()
 def main():
    client = FoundryChatClient(
        project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
-        model=os.environ["MODEL_DEPLOYMENT_NAME"],
-        credential=AzureCliCredential(),
+        model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
+        credential=DefaultAzureCredential(),
    )

    agent = Agent(
@@ -1,2 +0,0 @@
-FOUNDRY_PROJECT_ENDPOINT="..."
-MODEL_DEPLOYMENT_NAME="..."
@@ -1,27 +0,0 @@
-# Basic example of hosting an agent with the `responses` API and local tools
-
-This agent is equipped with a function tool and a local shell tool.
-
-> 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.
-
-## Running the server locally
-
-### Environment setup
-
-Follow the instructions in the [Environment setup](../../README.md#environment-setup) section of the README in the parent directory to set up your environment and install dependencies.
-
-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 "input" 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."}'
-```
@@ -0,0 +1,2 @@
+FOUNDRY_PROJECT_ENDPOINT="..."
+AZURE_AI_MODEL_DEPLOYMENT_NAME="..."
@@ -0,0 +1,33 @@
+# What this sample demonstrates
+
+An [Agent Framework](https://github.com/microsoft/agent-framework) agent with **locally-defined Python tools** hosted using the **Responses protocol**. It shows how to define custom tools with the `@tool` decorator and register them with the agent so the model can call them during a conversation.
+
+## How It Works
+
+### Model Integration
+
+The agent uses `FoundryChatClient` from the Agent Framework to create a Responses client from the project endpoint and model deployment. The agent supports both streaming (SSE events) and non-streaming (JSON) response modes.
+
+See [main.py](main.py) for the full implementation.
+
+### Agent Hosting
+
+The agent is hosted using the [Agent Framework](https://github.com/microsoft/agent-framework) with the `ResponsesHostServer`, which provisions a REST API endpoint compatible with the OpenAI Responses protocol.
+
+## Running the Agent Host
+
+Follow the instructions in the [Running the Agent Host Locally](../../README.md#running-the-agent-host-locally) section of the README in the parent directory to run the agent host.
+
+## Interacting with the agent
+
+> Depending on how you run the agent host, you can invoke the agent using `curl` (`Invoke-WebRequest` in PowerShell) or `azd`. Please refer to the [parent README](../../README.md) for more details. Use this README for sample queries you can send to 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?"}'
+```
+
+## Deploying the Agent to Foundry
+
+To host the agent on Foundry, follow the instructions in the [Deploying the Agent to Foundry](../../README.md#deploying-the-agent-to-foundry) section of the README in the parent directory.
@@ -1,4 +1,4 @@
-name: agent-framework-agent-with-local-tools
+name: agent-framework-agent-with-local-tools-responses
 description: >
  An Agent Framework agent with local tools hosted by Foundry.
 metadata:
@@ -9,15 +9,15 @@ metadata:
    - Responses Protocol
    - Streaming
 template:
-  name: agent-framework-agent-with-local-tools
+  name: agent-framework-agent-with-local-tools-responses
  kind: hosted
  protocols:
    - protocol: responses
      version: 1.0.0
  environment_variables:
-    - name: MODEL_DEPLOYMENT_NAME
-      value: "{{MODEL_DEPLOYMENT_NAME}}"
+    - name: AZURE_AI_MODEL_DEPLOYMENT_NAME
+      value: "{{AZURE_AI_MODEL_DEPLOYMENT_NAME}}"
 resources:
  - kind: model
    id: gpt-4.1-mini
-    name: MODEL_DEPLOYMENT_NAME
+    name: AZURE_AI_MODEL_DEPLOYMENT_NAME
@@ -1,5 +1,5 @@
 kind: hosted
-name: agent-framework-agent-with-local-tools
+name: agent-framework-agent-with-local-tools-responses
 protocols:
  - protocol: responses
    version: 1.0.0
@@ -8,7 +8,7 @@ from typing import Annotated
 from agent_framework import Agent, tool
 from agent_framework.foundry import FoundryChatClient
 from agent_framework_foundry_hosting import ResponsesHostServer
-from azure.identity import AzureCliCredential
+from azure.identity import DefaultAzureCredential
 from dotenv import load_dotenv
 from pydantic import Field

@@ -52,8 +52,8 @@ def run_bash(command: str) -> str:
 def main():
    client = FoundryChatClient(
        project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
-        model=os.environ["MODEL_DEPLOYMENT_NAME"],
-        credential=AzureCliCredential(),
+        model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
+        credential=DefaultAzureCredential(),
    )

    agent = Agent(
@@ -1,4 +1,3 @@
 FOUNDRY_PROJECT_ENDPOINT="..."
-MODEL_DEPLOYMENT_NAME="..."
-TOOLBOX_NAME="..."
+AZURE_AI_MODEL_DEPLOYMENT_NAME="..."
 GITHUB_PAT="..."
@@ -0,0 +1,33 @@
+# What this sample demonstrates
+
+An [Agent Framework](https://github.com/microsoft/agent-framework) agent that connects to a **remote MCP server** (GitHub) for tool discovery and hosted using the **Responses protocol**. Instead of defining tools locally, the agent discovers and invokes tools at runtime from an MCP-compatible endpoint — in this case, the GitHub Copilot MCP server. This enables dynamic tool integration without redeployment.
+
+## How It Works
+
+### Model Integration
+
+The agent uses `FoundryChatClient` from the Agent Framework to create an OpenAI-compatible Responses client. It registers a remote MCP tool pointing at `https://api.githubcopilot.com/mcp/`, authenticating with a GitHub Personal Access Token (PAT). When the model decides to call a tool, the framework forwards the call to the MCP server and returns the result to the model for the final reply.
+
+See [main.py](main.py) for the full implementation.
+
+### Agent Hosting
+
+The agent is hosted using the [Agent Framework](https://github.com/microsoft/agent-framework) with the `ResponsesHostServer`, which provisions a REST API endpoint compatible with the OpenAI Responses protocol.
+
+## Running the Agent Host
+
+Follow the instructions in the [Running the Agent Host Locally](../../README.md#running-the-agent-host-locally) section of the README in the parent directory to run the agent host.
+
+## Interacting with the agent
+
+> Depending on how you run the agent host, you can invoke the agent using `curl` (`Invoke-WebRequest` in PowerShell) or `azd`. Please refer to the [parent README](../../README.md) for more details. Use this README for sample queries you can send to 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."}'
+```
+
+## Deploying the Agent to Foundry
+
+To host the agent on Foundry, follow the instructions in the [Deploying the Agent to Foundry](../../README.md#deploying-the-agent-to-foundry) section of the README in the parent directory.
@@ -1,4 +1,4 @@
-name: agent-framework-agent-with-remote-mcp-tools
+name: agent-framework-agent-with-remote-mcp-tools-responses
 description: >
  An Agent Framework agent with remote MCP tools hosted by Foundry.
 metadata:
@@ -9,19 +9,17 @@ metadata:
    - Responses Protocol
    - Streaming
 template:
-  name: agent-framework-agent-with-remote-mcp-tools
+  name: agent-framework-agent-with-remote-mcp-tools-responses
  kind: hosted
  protocols:
    - protocol: responses
      version: 1.0.0
  environment_variables:
-    - name: MODEL_DEPLOYMENT_NAME
-      value: "{{MODEL_DEPLOYMENT_NAME}}"
+    - name: AZURE_AI_MODEL_DEPLOYMENT_NAME
+      value: "{{AZURE_AI_MODEL_DEPLOYMENT_NAME}}"
    - name: GITHUB_PAT
      value: ${GITHUB_PAT}
-    - name: TOOLBOX_NAME
-      value: ${TOOLBOX_NAME}
 resources:
  - kind: model
    id: gpt-4.1-mini
-    name: MODEL_DEPLOYMENT_NAME
+    name: AZURE_AI_MODEL_DEPLOYMENT_NAME
@@ -0,0 +1,11 @@
+kind: hosted
+name: agent-framework-agent-with-remote-mcp-tools-responses
+protocols:
+  - protocol: responses
+    version: 1.0.0
+resources:
+  cpu: "0.25"
+  memory: 0.5Gi
+environment_variables:
+  - name: GITHUB_PAT
+    value: ${GITHUB_PAT}
@@ -0,0 +1,56 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+import logging
+import os
+
+from agent_framework import Agent, ToolTypes
+from agent_framework.foundry import FoundryChatClient
+from agent_framework_foundry_hosting import ResponsesHostServer
+from azure.identity import DefaultAzureCredential
+from dotenv import load_dotenv
+
+# Load environment variables from .env file
+load_dotenv()
+
+logger = logging.getLogger(__name__)
+
+
+def main():
+    client = FoundryChatClient(
+        project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
+        model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
+        credential=DefaultAzureCredential(),
+    )
+
+    github_pat = os.environ["GITHUB_PAT"]
+    tools: list[ToolTypes] = []
+    if not github_pat:
+        logger.warning("GITHUB_PAT environment variable is not set. The GitHub MCP tool will not get registered.")
+    else:
+        tools.append(
+            client.get_mcp_tool(
+                name="GitHub",
+                url="https://api.githubcopilot.com/mcp/",
+                headers={
+                    "Authorization": f"Bearer {github_pat}",
+                },
+                approval_mode="never_require",
+            )
+        )
+
+    agent = Agent(
+        client=client,
+        instructions="You are a friendly assistant. Keep your answers brief.",
+        tools=tools,
+        # 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)
+    server.run()
+
+
+if __name__ == "__main__":
+    main()
@@ -1,25 +0,0 @@
-# Basic example of hosting an agent with the `responses` API and a remote MCP
-
-This agent is equipped with a GitHub MCP server and a Foundry Toolbox, which are both remote MCPs.
-
-> Note that there are other ways to interact with Foundry toolboxes. Using it as a MCP is just one of the options.
-
-## Running the server locally
-
-### Environment setup
-
-Follow the instructions in the [Environment setup](../../README.md#environment-setup) section of the README in the parent directory to set up your environment and install dependencies.
-
-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 "input" 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."}'
-```
@@ -1,76 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-import os
-
-import httpx
-from agent_framework import Agent, MCPStreamableHTTPTool
-from agent_framework.foundry import FoundryChatClient
-from agent_framework_foundry_hosting import ResponsesHostServer
-from azure.identity import AzureCliCredential
-from dotenv import load_dotenv
-
-# Load environment variables from .env file
-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["MODEL_DEPLOYMENT_NAME"],
-        credential=AzureCliCredential(),
-    )
-
-    # Foundry Toolbox as a MCP tool
-    project_endpoint = os.environ["FOUNDRY_PROJECT_ENDPOINT"]
-    toolbox_name = os.environ["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"
-        )
-
-    github_mcp_tool = client.get_mcp_tool(
-        name="GitHub",
-        url="https://api.githubcopilot.com/mcp/",
-        headers={
-            "Authorization": f"Bearer {github_pat}",
-        },
-        approval_mode="never_require",
-    )
-
-    agent = Agent(
-        client=client,
-        instructions="You are a friendly assistant. Keep your answers brief.",
-        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
-        default_options={"store": False},
-    )
-
-    server = ResponsesHostServer(agent)
-    server.run()
-
-
-if __name__ == "__main__":
-    main()
@@ -0,0 +1,3 @@
+FOUNDRY_PROJECT_ENDPOINT="..."
+AZURE_AI_MODEL_DEPLOYMENT_NAME="..."
+TOOLBOX_NAME="..."
@@ -0,0 +1,43 @@
+# What this sample demonstrates
+
+An [Agent Framework](https://github.com/microsoft/agent-framework) agent that uses **Foundry Toolbox** for tool discovery and hosted using the **Responses protocol**. Foundry Toolbox is a managed tool registry in Microsoft Foundry that lets you define tools centrally and share them across agents.
+
+## Creating a Foundry Toolbox
+
+You can create a Foundry Toolbox by code. Refer to this sample for an example: [Foundry Toolbox CRUD Sample](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-projects/samples/hosted_agents/sample_toolboxes_crud.py).
+
+You can also create a Foundry Toolbox in the Foundry portal. Read more about it [in the Foundry toolbox documentation](https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/toolbox).
+
+> If you set up a project with this sample and provision the resources using `azd provision`, a Foundry Toolbox will be created with the specified tools in [`agent.manifest.yaml`](agent.manifest.yaml).
+
+## How It Works
+
+### Model Integration
+
+The agent uses `FoundryChatClient` from the Agent Framework to create an OpenAI-compatible Responses client. It loads a named Foundry Toolbox via `client.get_toolbox(name)` — the toolbox is a server-side bundle of tool configurations (e.g., `code_interpreter`, `web_search`) defined in the Foundry portal or by `azd provision`. Omitting `version` resolves the toolbox's current default version at runtime.
+
+The sample then narrows the toolbox to a subset of tool types via `select_toolbox_tools(toolbox, include_types=[...])` before handing it to the agent. This demonstrates how one toolbox can be reused across agents that each expose only the tools they need — here, the agent only sees `code_interpreter` even though the toolbox also includes `web_search`.
+
+See [main.py](main.py) for the full implementation.
+
+### Agent Hosting
+
+The agent is hosted using the [Agent Framework](https://github.com/microsoft/agent-framework) with the `ResponsesHostServer`, which provisions a REST API endpoint compatible with the OpenAI Responses protocol.
+
+## Running the Agent Host
+
+Follow the instructions in the [Running the Agent Host Locally](../../README.md#running-the-agent-host-locally) section of the README in the parent directory to run the agent host.
+
+## Interacting with the agent
+
+> Depending on how you run the agent host, you can invoke the agent using `curl` (`Invoke-WebRequest` in PowerShell) or `azd`. Please refer to the [parent README](../../README.md) for more details. Use this README for sample queries you can send to 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 tools do you have?"}'
+```
+
+## Deploying the Agent to Foundry
+
+To host the agent on Foundry, follow the instructions in the [Deploying the Agent to Foundry](../../README.md#deploying-the-agent-to-foundry) section of the README in the parent directory.
@@ -0,0 +1,33 @@
+name: agent-framework-agent-with-foundry-toolbox-responses
+description: >
+  An Agent Framework agent with Foundry Toolbox integration.
+metadata:
+  tags:
+    - Agent Framework
+    - AI Agent Hosting
+    - Azure AI AgentServer
+    - Responses Protocol
+    - Streaming
+template:
+  name: agent-framework-agent-with-foundry-toolbox-responses
+  kind: hosted
+  protocols:
+    - protocol: responses
+      version: 1.0.0
+  environment_variables:
+    - name: AZURE_AI_MODEL_DEPLOYMENT_NAME
+      value: "{{AZURE_AI_MODEL_DEPLOYMENT_NAME}}"
+    - name: TOOLBOX_NAME
+      value: "agent-tools"
+resources:
+  - kind: model
+    id: gpt-4.1-mini
+    name: AZURE_AI_MODEL_DEPLOYMENT_NAME
+  - kind: toolbox
+    name: agent-tools
+    tools:
+      - type: web_search
+        name: web_search
+      - type: code_interpreter
+        name: code_interpreter
+
@@ -1,5 +1,5 @@
 kind: hosted
-name: agent-framework-agent-with-remote-mcp-tools
+name: agent-framework-agent-with-foundry-toolbox-responses
 protocols:
  - protocol: responses
    version: 1.0.0
@@ -0,0 +1,42 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+import asyncio
+import os
+
+from agent_framework import Agent
+from agent_framework.foundry import FoundryChatClient
+from agent_framework_foundry_hosting import ResponsesHostServer
+from azure.identity import DefaultAzureCredential
+from dotenv import load_dotenv
+
+# Load environment variables from .env file
+load_dotenv()
+
+
+async def main():
+    client = FoundryChatClient(
+        project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
+        model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
+        credential=DefaultAzureCredential(),
+    )
+
+    # Load the named toolbox from the Foundry project. Omitting `version`
+    # resolves the toolbox's current default version at runtime.
+    toolbox = await client.get_toolbox(os.environ["TOOLBOX_NAME"])
+
+    agent = Agent(
+        client=client,
+        instructions="You are a friendly assistant. Keep your answers brief.",
+        tools=toolbox,
+        # 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)
+    await server.run_async()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
@@ -0,0 +1,2 @@
+agent-framework
+agent-framework-foundry-hosting
@@ -1,2 +0,0 @@
-FOUNDRY_PROJECT_ENDPOINT="..."
-MODEL_DEPLOYMENT_NAME="..."
@@ -1,23 +0,0 @@
-# Basic example of hosting an agent with the `responses` API and a workflow
-
-This sample demonstrates how to host a workflow using the `responses` API.
-
-## Running the server locally
-
-### Environment setup
-
-Follow the instructions in the [Environment setup](../../README.md#environment-setup) section of the README in the parent directory to set up your environment and install dependencies.
-
-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 "input" 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."}'
-```
@@ -0,0 +1,6 @@
+.venv
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.Python
@@ -0,0 +1,2 @@
+FOUNDRY_PROJECT_ENDPOINT="..."
+AZURE_AI_MODEL_DEPLOYMENT_NAME="..."
@@ -0,0 +1,16 @@
+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"]
@@ -0,0 +1,43 @@
+# What this sample demonstrates
+
+An [Agent Framework](https://github.com/microsoft/agent-framework) workflow demonstrating **multi-agent chaining** and hosted using the **Responses protocol**. It shows how to use the Agent Framework's `WorkflowBuilder` to compose a pipeline of specialized agents — a slogan writer, a legal reviewer, and a formatter — that process a request sequentially. Each agent receives only the output of the previous agent, and only the final formatted result is returned to the caller.
+
+> The workflow will be used as an agent. Read more about Agent Framework workflows in the [Agent Framework documentation](https://learn.microsoft.com/en-us/agent-framework/workflows/) and workflow as an agent in the [Workflow as an Agent documentation](https://learn.microsoft.com/en-us/agent-framework/workflows/as-agents?pivots=programming-language-python).
+
+> This sample requires a more advanced model because the model needs to continue the conversation from an assistant message. Not all models perform well in this scenario. Tested with OpenAI's model `gpt-5.4`.
+
+## How It Works
+
+### Model Integration
+
+The agent creates three specialized `Agent` instances sharing the same `FoundryChatClient`: a **writer** that generates slogans, a **legal reviewer** that ensures compliance, and a **formatter** that styles the output. Each agent is wrapped in an `AgentExecutor` with `context_mode="last_agent"` so it only sees the previous agent's output. The `WorkflowBuilder` wires them into a linear pipeline and limits the output to the formatter's result.
+
+See [main.py](main.py) for the full implementation.
+
+### Agent Hosting
+
+The workflow is exposed as a single agent via `.as_agent()` and hosted using the [Agent Framework](https://github.com/microsoft/agent-framework) with the `ResponsesHostServer`, which provisions a REST API endpoint compatible with the OpenAI Responses protocol.
+
+## Running the Agent Host
+
+Follow the instructions in the [Running the Agent Host Locally](../../README.md#running-the-agent-host-locally) section of the README in the parent directory to run the agent host.
+
+## Interacting with the agent
+
+> Depending on how you run the agent host, you can invoke the agent using `curl` (`Invoke-WebRequest` in PowerShell) or `azd`. Please refer to the [parent README](../../README.md) for more details. Use this README for sample queries you can send to 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 "Create a slogan for a new electric SUV that is affordable and fun to drive."
+```
+
+## Deploying the Agent to Foundry
+
+To host the agent on Foundry, follow the instructions in the [Deploying the Agent to Foundry](../../README.md#deploying-the-agent-to-foundry) section of the README in the parent directory.
@@ -1,4 +1,4 @@
-name: agent-framework-workflows
+name: agent-framework-workflows-responses
 description: >
  An Agent Framework workflow hosted by Foundry.
 metadata:
@@ -9,15 +9,15 @@ metadata:
    - Responses Protocol
    - Streaming
 template:
-  name: agent-framework-workflows
+  name: agent-framework-workflows-responses
  kind: hosted
  protocols:
    - protocol: responses
      version: 1.0.0
  environment_variables:
-    - name: MODEL_DEPLOYMENT_NAME
-      value: "{{MODEL_DEPLOYMENT_NAME}}"
+    - name: AZURE_AI_MODEL_DEPLOYMENT_NAME
+      value: "{{AZURE_AI_MODEL_DEPLOYMENT_NAME}}"
 resources:
  - kind: model
-    id: gpt-4.1-mini
-    name: MODEL_DEPLOYMENT_NAME
+    id: gpt-5.4
+    name: AZURE_AI_MODEL_DEPLOYMENT_NAME
@@ -1,5 +1,5 @@
 kind: hosted
-name: agent-framework-workflows
+name: agent-framework-workflows-responses
 protocols:
  - protocol: responses
    version: 1.0.0
@@ -5,7 +5,7 @@ import os
 from agent_framework import Agent, AgentExecutor, WorkflowBuilder
 from agent_framework.foundry import FoundryChatClient
 from agent_framework_foundry_hosting import ResponsesHostServer
-from azure.identity import AzureCliCredential
+from azure.identity import DefaultAzureCredential
 from dotenv import load_dotenv

 # Load environment variables from .env file
@@ -15,8 +15,8 @@ load_dotenv()
 def main():
    client = FoundryChatClient(
        project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
-        model=os.environ["MODEL_DEPLOYMENT_NAME"],
-        credential=AzureCliCredential(),
+        model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
+        credential=DefaultAzureCredential(),
    )

    writer_agent = Agent(
@@ -1,11 +1,215 @@
-# Hosting agents with Foundry Hosting and the `responses` API
+# Foundry Hosted Agent Samples

-This folder contains a list of samples that show how to host agents using the `responses` API and deploy them to Foundry Hosting.
+This directory contains samples that demonstrate how to use hosted [Agent Framework](https://github.com/microsoft/agent-framework) agents with different capabilities and configurations on Foundry using the Foundry Hosting Agent service. Each sample includes a README with instructions on how to set up, run, and interact with the agent.

-| 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 Toolbox. |
-| [04_workflows](./04_workflows) | An example of hosting a workflow with the `responses` API. |
-| [using_deployed_agent.py](./using_deployed_agent.py) | Connect to the deployed basic Foundry agent with `FoundryAgent`, `allow_preview=True`, and version `v2`. |
+## Samples
+
+### Responses API
+
+| # | Sample | Description |
+|---|--------|-------------|
+| 1 | [Basic](responses/01_basic/) | A minimal agent demonstrating basic request/response interaction and multi-turn conversations using `previous_response_id`. |
+| 2 | [Tools](responses/02_tools/) | An agent with local tools (e.g., weather lookup), demonstrating how to register and invoke custom tool functions alongside the LLM. |
+| 3 | [MCP](responses/03_mcp/) | An agent connected to a remote MCP server (GitHub), demonstrating external MCP tool provider integration. |
+| 4 | [Foundry Toolbox](responses/04_foundry_toolbox/) | An agent using Azure Foundry Toolbox, demonstrating toolbox provisioning and querying available tools at runtime. |
+| 5 | [Workflows](responses/05_workflows/) | An agent with a multi-step orchestrated workflow, demonstrating chaining prompts through an orchestrated flow. |
+
+### Invocations API
+
+| # | Sample | Description |
+|---|--------|-------------|
+| 1 | [Basic](invocations/01_basic/) | A minimal agent demonstrating session state management via `agent_session_id` in URL params/response headers. |
+| 2 | [Break Glass](invocations/02_break_glass/) | An agent demonstrating a "break glass" scenario where customizations of the API behaviors are needed, allowing for more direct control over how requests and responses are handled by the hosting layer. |
+
+## Running the Agent Host Locally
+
+### Using `azd`
+
+#### Prerequisites
+
+1. **Azure Developer CLI (`azd`)**
+
+    - [Install azd](https://learn.microsoft.com/en-us/azure/developer/azure-developer-cli/install-azd) and the AI agent extension: `azd ext install azure.ai.agents`
+    - Authenticated: `azd auth login`
+
+2. **Azure Subscription**
+
+#### Create a new project
+
+**No cloning required**. Create a new folder, point azd at the manifest on GitHub.
+
+```bash
+mkdir hosted-agent-framework-agent && cd hosted-agent-framework-agent
+
+# Initialize from the manifest
+azd ai agent init -m https://github.com/microsoft/agent-framework/blob/main/python/samples/04-hosting/foundry-hosted-agents/responses/01_basic/agent.manifest.yaml
+```
+
+Follow the instructions from `azd ai agent init` to complete the agent initialization. If you don't have an existing Foundry project and a model deployment, `azd ai agent init` will guide you through creating them.
+
+#### Provision Azure Resources
+
+> This step is only needed if you don't have an existing Foundry project and model deployment.
+
+Run the following command to provision the necessary Azure resources:
+
+```bash
+azd provision
+```
+
+This will create the following Azure resources:
+
+- A new resource group named `rg-[project_name]-dev`. In this guide, `[project_name]` will be `hosted-agent-framework-agent`.
+- Within the resource group, among other resources, the most important ones are:
+  - A new Foundry instance
+  - A new Foundry project, within which a new model deployment will be created
+  - An Application Insights instance
+  - A container registry, which will be used to store the container images for the hosted agent
+
+#### Set Environment Variables
+
+```bash
+export FOUNDRY_PROJECT_ENDPOINT="https://<account>.services.ai.azure.com/api/projects/<project>"
+export AZURE_AI_MODEL_DEPLOYMENT_NAME="<your-model-deployment-name>"
+# And any other environment variables required by the sample
+```
+
+Or in PowerShell:
+
+```powershell
+$env:FOUNDRY_PROJECT_ENDPOINT="https://<account>.services.ai.azure.com/api/projects/<project>"
+$env:AZURE_AI_MODEL_DEPLOYMENT_NAME="<your-model-deployment-name>"
+# And any other environment variables required by the sample
+```
+
+> Note: The environment variables set above are only for the current session. You will need to set them again if you open a new terminal session. if you want to set the environment variables permanently in the azd environment, you can use `azd env set <name> <value>`.
+
+#### Running the Agent Host
+
+```bash
+azd ai agent run
+```
+
+Right now, the agent host should be running on `http://localhost:8088`
+
+#### Invoking the Agent
+
+Open another terminal, **navigate to the project directory**, and run the following command to invoke the agent:
+
+```bash
+azd ai agent invoke --local "Hello!"
+```
+
+Or you can in another terminal, without navigating to the project directory, run the following command to invoke the agent:
+
+```bash
+curl -X POST http://localhost:8088/responses -H "Content-Type: application/json" -d '{"input": "Hello!"}'
+```
+
+Or in PowerShell:
+
+```powershell
+(Invoke-WebRequest -Uri http://localhost:8088/responses -Method POST -ContentType "application/json" -Body '{"input": "Hello!"}').Content
+```
+
+### Using `python`
+
+#### Prerequisites
+
+1. An existing Foundry project
+2. A deployed model in your Foundry project
+3. Azure CLI installed and authenticated
+4. Python 3.10 or later
+
+#### Running the Agent Host with Python
+
+Clone the repository containing the sample code:
+
+```bash
+git clone https://github.com/microsoft/agent-framework.git
+cd agent-framework/python/samples/04-hosting/foundry-hosted-agents/responses
+```
+
+#### Environment setup
+
+1. Navigate to the sample directory you want to explore. Create a virtual environment:
+
+   ```bash
+   python -m venv .venv
+
+   # Windows
+   .venv\Scripts\Activate
+
+   # macOS/Linux
+   source .venv/bin/activate
+   ```
+
+2. Install dependencies:
+
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+3. Create a `.env` file with your Foundry configuration following the `env.example` file in the sample.
+
+4. Make sure you are logged in with the Azure CLI:
+
+   ```bash
+   az login
+   ```
+
+#### Running the Agent Host
+
+```bash
+python main.py
+```
+
+Right now, the agent host should be running on `http://localhost:8088`
+
+#### Invoking the Agent
+
+On another terminal, run the following command to invoke the agent:
+
+```bash
+curl -X POST http://localhost:8088/responses -H "Content-Type: application/json" -d '{"input": "Hello!"}'
+```
+
+Or in PowerShell:
+
+```powershell
+(Invoke-WebRequest -Uri http://localhost:8088/responses -Method POST -ContentType "application/json" -Body '{"input": "Hello!"}').Content
+```
+
+## Deploying the Agent to Foundry
+
+Once you've tested locally, deploy to Microsoft Foundry.
+
+### With an Existing Foundry Project
+
+If you already have a Foundry project and the necessary Azure resources provisioned, you can skip the setup steps and proceed directly to deploying the agent.
+
+After running `azd ai agent init -m <agent.manifest.yaml>` and following the prompts to configure your agent, you will have a project ready for deployment.
+
+### Setting Up a New Foundry Project
+
+Follow the steps in [Using `azd`](#using-azd) to set up the project and provision the necessary Azure resources for your Foundry deployment.
+
+### Deploying the Agent
+
+Once the project is setup and resources are provisioned, you can deploy the agent to Foundry by running:
+
+```bash
+azd deploy
+```
+
+> The Foundry hosting infrastructure will inject the following environment variables into your agent at runtime:
+>
+> - `FOUNDRY_PROJECT_ENDPOINT`: The endpoint URL for the Foundry project where the agent is deployed.
+> - `AZURE_AI_MODEL_DEPLOYMENT_NAME`: The name of the model deployment in your Foundry project. This is configured during the agent initialization process with `azd ai agent init`.
+> - `APPLICATIONINSIGHTS_CONNECTION_STRING`: The connection string for Application Insights to enable telemetry for your agent.
+
+This will package your agent and deploy it to the Foundry environment, making it accessible through the Foundry project endpoint. Once it's deployed, you can also access the agent through the Foundry UI.
+
+For the full deployment guide, see the [official deployment guide](https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/deploy-hosted-agent).
+
+Once deployed, learn more about how to manage deployed agents in the [official management guide](https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/manage-hosted-agent).