Python: Anthropic foundry (#2302)

* added anthropic foundry sample

* updated readme

* typo

Author: eavanvalkenburg

python/samples/getting_started/agents/anthropic/README.md

@@ -9,10 +9,16 @@ This folder contains examples demonstrating how to use Anthropic's Claude models
 | [`anthropic_basic.py`](anthropic_basic.py) | Demonstrates how to setup a simple agent using the AnthropicClient, with both streaming and non-streaming responses. |
 | [`anthropic_advanced.py`](anthropic_advanced.py) | Shows advanced usage of the AnthropicClient, including hosted tools and `thinking`. |
 | [`anthropic_skills.py`](anthropic_skills.py) | Illustrates how to use Anthropic-managed Skills with an agent, including the Code Interpreter tool and file generation and saving. |
+| [`anthropic_foundry.py`](anthropic_foundry.py) | Example of using Foundry's Anthropic integration with the Agent Framework. |
 
 ## Environment Variables
 
 Set the following environment variables before running the examples:
 
 - `ANTHROPIC_API_KEY`: Your Anthropic API key (get one from [Anthropic Console](https://console.anthropic.com/))
-- `ANTHROPIC_MODEL`: The Claude model to use (e.g., `claude-haiku-4-5`, `claude-sonnet-4-5-20250929`)
+- `ANTHROPIC_CHAT_MODEL_ID`: The Claude model to use (e.g., `claude-haiku-4-5`, `claude-sonnet-4-5-20250929`)
+
+Or, for Foundry:
+- `ANTHROPIC_FOUNDRY_API_KEY`: Your Foundry Anthropic API key
+- `ANTHROPIC_FOUNDRY_ENDPOINT`: The endpoint URL for your Foundry Anthropic resource
+- `ANTHROPIC_CHAT_MODEL_ID`: The Claude model to use in Foundry (e.g., `claude-haiku-4-5`)

python/samples/getting_started/agents/anthropic/anthropic_foundry.py

@@ -0,0 +1,63 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+import asyncio
+
+from agent_framework import HostedMCPTool, HostedWebSearchTool, TextReasoningContent, UsageContent
+from agent_framework.anthropic import AnthropicClient
+from anthropic import AsyncAnthropicFoundry
+
+"""
+Anthropic Foundry Chat Agent Example
+
+This sample demonstrates using Anthropic with:
+- Setting up an Anthropic-based agent with hosted tools.
+- Using the `thinking` feature.
+- Displaying both thinking and usage information during streaming responses.
+
+This example requires `anthropic>=0.74.0` and an endpoint in Foundry for Anthropic.
+
+To use the Foundry integration ensure you have the following environment variables set:
+- ANTHROPIC_FOUNDRY_API_KEY
+    Alternatively you can pass in a azure_ad_token_provider function to the AsyncAnthropicFoundry constructor.
+- ANTHROPIC_FOUNDRY_ENDPOINT
+    Should be something like https://<your-resource-name>.services.ai.azure.com/anthropic/
+- ANTHROPIC_CHAT_MODEL_ID
+    Should be something like claude-haiku-4-5
+"""
+
+
+async def main() -> None:
+    """Example of streaming response (get results as they are generated)."""
+    agent = AnthropicClient(anthropic_client=AsyncAnthropicFoundry()).create_agent(
+        name="DocsAgent",
+        instructions="You are a helpful agent for both Microsoft docs questions and general questions.",
+        tools=[
+            HostedMCPTool(
+                name="Microsoft Learn MCP",
+                url="https://learn.microsoft.com/api/mcp",
+            ),
+            HostedWebSearchTool(),
+        ],
+        # anthropic needs a value for the max_tokens parameter
+        # we set it to 1024, but you can override like this:
+        max_tokens=20000,
+        additional_chat_options={"thinking": {"type": "enabled", "budget_tokens": 10000}},
+    )
+
+    query = "Can you compare Python decorators with C# attributes?"
+    print(f"User: {query}")
+    print("Agent: ", end="", flush=True)
+    async for chunk in agent.run_stream(query):
+        for content in chunk.contents:
+            if isinstance(content, TextReasoningContent):
+                print(f"\033[32m{content.text}\033[0m", end="", flush=True)
+            if isinstance(content, UsageContent):
+                print(f"\n\033[34m[Usage so far: {content.details}]\033[0m\n", end="", flush=True)
+        if chunk.text:
+            print(chunk.text, end="", flush=True)
+
+    print("\n")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())