mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00

Files

T

Eduard van Valkenburg 0cd40f8354 Python: [BREAKING] Refactor middleware layering and split Anthropic raw client (#4746 )

* [BREAKING] Refactor middleware layering and raw clients

Reorder chat client layers so function invocation wraps chat middleware, and chat middleware stays outside telemetry while still running for each inner model call. Add middleware pipeline caching, refresh docs and samples, and split Anthropic into raw and public clients to match the standard layering model.

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

* Tighten typing ignores in ancillary modules

Add targeted typing ignores in workflow visualization and lab modules so pyright stays clean alongside the middleware refactor work.

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

* Fix categorize_middleware to unpack tuple/Sequence and use relative MRO assertions

- Broaden isinstance check in categorize_middleware from list to Sequence
  so tuples and other Sequence types are properly unpacked instead of
  being appended as a single item.
- Replace fragile hardcoded MRO index assertions in anthropic test with
  relative ordering via mro.index().
- Add regression tests for categorize_middleware with tuple, list, and
  None inputs.

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

* Fix middleware string decomposition, add middleware param to FunctionInvocationLayer, and add tests (#4710)

- Guard categorize_middleware Sequence check against str/bytes to prevent
  character-by-character decomposition of accidentally passed strings
- Add explicit middleware parameter to FunctionInvocationLayer.get_response
  and merge it into client_kwargs before categorization, fixing the
  inconsistency where only OpenAIChatClient supported this parameter
- Add assertions that RawAnthropicClient does not inherit convenience layers
- Add chat middleware cache test with non-empty base middleware
- Add tests for single unwrapped middleware item and string input

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

* Apply pre-commit auto-fixes

* Apply pre-commit auto-fixes

* Address review feedback for #4710: review comment fixes

---------

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

0cd40f8354 · 2026-03-20 00:43:37 +00:00

History

built_in_chat_clients.py

Python: Add load_dotenv() to samples for .env file support (#4043 )

2026-02-19 10:55:13 +00:00

chat_response_cancellation.py

Python: Simplify Python Poe tasks and unify package selectors (#4722 )

2026-03-18 18:39:11 +00:00

custom_chat_client.py

Python: [BREAKING] Refactor middleware layering and split Anthropic raw client (#4746 )

2026-03-20 00:43:37 +00:00

README.md

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

2026-02-16 16:30:38 +00:00

README.md

Chat Client Examples

This folder contains examples for direct chat client usage patterns.

Examples

File	Description
`built_in_chat_clients.py`	Consolidated sample for built-in chat clients. Uses `get_client()` to create the selected client and pass it to `main()`.
`chat_response_cancellation.py`	Demonstrates how to cancel chat responses during streaming, showing proper cancellation handling and cleanup.
`custom_chat_client.py`	Demonstrates how to create custom chat clients by extending the `BaseChatClient` class. Shows a `EchoingChatClient` implementation and how to integrate it with `Agent` using the `as_agent()` method.

Selecting a built-in client

built_in_chat_clients.py starts with:

asyncio.run(main("openai_chat"))

Change the argument to pick a client:

openai_chat
openai_responses
openai_assistants
anthropic
ollama
bedrock
azure_openai_chat
azure_openai_responses
azure_openai_responses_foundry
azure_openai_assistants
azure_ai_agent

Example:

uv run samples/02-agents/chat_client/built_in_chat_clients.py

Environment Variables

Depending on the selected client, set the appropriate environment variables:

For Azure clients:

AZURE_OPENAI_ENDPOINT: Your Azure OpenAI endpoint
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: The name of your Azure OpenAI chat deployment
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME: The name of your Azure OpenAI responses deployment

For Azure OpenAI Foundry responses client (azure_openai_responses_foundry):

AZURE_AI_PROJECT_ENDPOINT: Your Azure AI project endpoint
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME: The name of your Azure OpenAI responses deployment

For Azure AI agent client (azure_ai_agent):

AZURE_AI_PROJECT_ENDPOINT: Your Azure AI project endpoint
AZURE_AI_MODEL_DEPLOYMENT_NAME: The name of your model deployment (used by azure_ai_agent)

For OpenAI clients:

OPENAI_API_KEY: Your OpenAI API key
OPENAI_CHAT_MODEL_ID: The OpenAI model for openai_chat and openai_assistants
OPENAI_RESPONSES_MODEL_ID: The OpenAI model for openai_responses

For Anthropic client (anthropic):

ANTHROPIC_API_KEY: Your Anthropic API key
ANTHROPIC_CHAT_MODEL_ID: The Anthropic model ID (for example, claude-sonnet-4-5)

For Ollama client (ollama):

OLLAMA_HOST: Ollama server URL (defaults to http://localhost:11434 if unset)
OLLAMA_MODEL_ID: Ollama model name (for example, mistral, qwen2.5:8b)

For Bedrock client (bedrock):

BEDROCK_CHAT_MODEL_ID: Bedrock model ID (for example, anthropic.claude-3-5-sonnet-20240620-v1:0)
BEDROCK_REGION: AWS region (defaults to us-east-1 if unset)
AWS credentials via standard environment variables (for example, AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY)