Python: Fix tool normalization and provider sample consolidation (#3953)

* Fix tool normalization and provider samples

- restore callable/single-tool normalization paths and unset tool-choice behavior\n- consolidate and expand chat/provider samples (OpenAI/Azure/Anthropic/Ollama/Bedrock)\n- migrate Bedrock lazy import surface to agent_framework.amazon and move provider samples

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* small fix in sample

* Finalize provider, samples, and core cleanup

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix CopilotTool passthrough in agent

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fix link

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

python/packages/bedrock/AGENTS.md

@@ -12,7 +12,7 @@ Integration with AWS Bedrock for LLM inference.
 ## Usage
 
 ```python
-from agent_framework_bedrock import BedrockChatClient
+from agent_framework.amazon import BedrockChatClient
 
 client = BedrockChatClient(model_id="anthropic.claude-3-sonnet-20240229-v1:0")
 response = await client.get_response("Hello")
@@ -21,5 +21,5 @@ response = await client.get_response("Hello")
 ## Import Path
 
 ```python
-from agent_framework_bedrock import BedrockChatClient
+from agent_framework.amazon import BedrockChatClient
 ```

python/packages/bedrock/README.md

@@ -12,7 +12,7 @@ The Bedrock integration enables Microsoft Agent Framework applications to call A
 
 ### Basic Usage Example
 
-See the [Bedrock sample script](samples/bedrock_sample.py) for a runnable end-to-end script that:
+See the [Bedrock sample](../../samples/02-agents/providers/amazon/bedrock_chat_client.py) for a runnable end-to-end script that:
 
 - Loads credentials from the `BEDROCK_*` environment variables
 - Instantiates `BedrockChatClient`

python/packages/bedrock/agent_framework_bedrock/_chat_client.py

@@ -260,7 +260,7 @@ class BedrockChatClient(
         Examples:
             .. code-block:: python
 
-                from agent_framework.bedrock import BedrockChatClient
+                from agent_framework.amazon import BedrockChatClient
 
                 # Basic usage with default credentials
                 client = BedrockChatClient(model_id="<model name>")

python/packages/bedrock/samples/bedrock_sample.py

@@ -1,45 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-import asyncio
-import logging
-
-from agent_framework import Agent, tool
-
-from agent_framework_bedrock import BedrockChatClient
-
-
-@tool(approval_mode="never_require")
-def get_weather(city: str) -> dict[str, str]:
-    """Return a mock forecast for the requested city."""
-    normalized = city.strip() or "New York"
-    return {"city": normalized, "forecast": "72F and sunny"}
-
-
-async def main() -> None:
-    """Run the Bedrock sample agent, invoke the weather tool, and log the response."""
-    agent = Agent(
-        client=BedrockChatClient(),
-        instructions="You are a concise travel assistant.",
-        name="BedrockWeatherAgent",
-        tool_choice="auto",
-        tools=[get_weather],
-    )
-
-    response = await agent.run("Use the weather tool to check the forecast for new york.")
-    logging.info("\nAssistant reply:", response.text or "<no text returned>")
-    logging.info("\nConversation transcript:")
-    for message in response.messages:
-        for idx, content in enumerate(message.contents, start=1):
-            match content.type:
-                case "text":
-                    logging.info(f"  {idx}. text -> {content.text}")
-                case "function_call":
-                    logging.info(f"  {idx}. function_call ({content.name}) -> {content.arguments}")
-                case "function_result":
-                    logging.info(f"  {idx}. function_result ({content.call_id}) -> {content.result}")
-                case _:
-                    logging.info(f"  {idx}. {content.type}")
-
-
-if __name__ == "__main__":
-    asyncio.run(main())