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

Files

T

Eduard van Valkenburg 1e350ea22f Python: [BREAKING] PR2 — Wire context provider pipeline, remove old types, update all consumers (#3850 )

* PR2: Wire context provider pipeline and update all internal consumers

- Replace AgentThread with AgentSession across all packages
- Replace ContextProvider with BaseContextProvider across all packages
- Replace context_provider param with context_providers (Sequence)
- Replace thread= with session= in run() signatures
- Replace get_new_thread() with create_session()
- Add get_session(service_session_id) to agent interface
- DurableAgentThread -> DurableAgentSession
- Remove _notify_thread_of_new_messages from WorkflowAgent
- Wire before_run/after_run context provider pipeline in RawAgent
- Auto-inject InMemoryHistoryProvider when no providers configured

* fix: update all tests for context provider pipeline, fix lazy-loaders, remove old test files

* refactor: update all sample files for context provider pipeline (AgentThread→AgentSession, ContextProvider→BaseContextProvider)

* fix: update remaining ag-ui references (client docstring, getting_started sample)

* fix: make get_session service_session_id keyword-only to avoid confusion with session_id

* refactor: rename _RunContext.thread_messages to session_messages

* refactor: remove _threads.py, _memory.py, and old provider files; migrate devui to use plain message lists

* rename: remove _new_ prefix from test files

* refactor: rewrite SlidingWindowChatMessageStore as SlidingWindowHistoryProvider(InMemoryHistoryProvider)

* fix: read full history from session state directly instead of reaching into provider internals

* fix: update stale .pyi stubs, sample imports, and README references for new provider types

* fix: remove stale message_store, _notify_thread_of_new_messages, and session_id.key references in samples

* refactor: merge context_providers and sessions sample folders into sessions, remove aggregate_context_provider

* refactor: UserInfoMemory stores state in session.state instead of instance attributes

* feat: add Pydantic BaseModel support to session state serialization

Pydantic models stored in session.state are now automatically serialized
via model_dump() and restored via model_validate() during to_dict()/from_dict()
round-trips. Models are auto-registered on first serialization; use
register_state_type() for cold-start deserialization.

Also export register_state_type as a public API.

* fix mem0

* Update sample README links and descriptions for session terminology

- Replace 'thread' with 'session' in sample descriptions across all READMEs
- Update file links for renamed samples (mem0_sessions, redis_sessions, etc.)
- Fix Threads section → Sessions section in main samples/README.md
- Update tools, middleware, workflows, durabletask, azure_functions READMEs
- Update architecture diagrams in concepts/tools/README.md
- Update migration guides (autogen, semantic-kernel)

* Fix broken Redis README link to renamed sample

* Fix Mem0 OSS client search: pass scoping params as direct kwargs

AsyncMemory (OSS) expects user_id/agent_id/run_id as direct kwargs,
while AsyncMemoryClient (Platform) expects them in a filters dict.
Adds tests for both client types.

Port of fix from #3844 to new Mem0ContextProvider.

* Fix rebase issues: restore missing _conversation_state.py and checkpoint decode logic

- Add back _conversation_state.py (encode/decode_chat_messages) lost in rebase
- Fix on_checkpoint_restore to decode cache/conversation with decode_chat_messages
- Fix on_checkpoint_restore to use decode_checkpoint_value for pending requests
- Add tests/workflow/__init__.py for relative import support
- Fix test_agent_executor checkpoint selection (checkpoints[1] not superstep)

* Add STORES_BY_DEFAULT ClassVar to skip redundant InMemoryHistoryProvider injection

Chat clients that store history server-side by default (OpenAI Responses API,
Azure AI Agent) now declare STORES_BY_DEFAULT = True. The agent checks this
during auto-injection and skips InMemoryHistoryProvider unless the user
explicitly sets store=False.

* Fix broken markdown links in azure_ai and redis READMEs

* Fix getting-started samples to use session API instead of removed thread/ContextProvider API

* updates to workflow as agent

* fix group chat import

* Rename Thread→Session throughout, fix service_session_id propagation, remove stale AGUIThread

- Fix: Propagate conversation_id from ChatResponse back to session.service_session_id
  in both streaming and non-streaming paths in _agents.py
- Rename AgentThreadException → AgentSessionException
- Remove stale AGUIThread from ag_ui lazy-loader
- Rename use_service_thread → use_service_session in ag-ui package
- Rename test functions from *_thread_* to *_session_*
- Rename sample files from *_thread* to *_session*
- Update docstrings and comments: thread → session
- Update _mcp.py kwargs filter: add 'session' alongside 'thread'
- Fix ContinuationToken docstring example: thread=thread → session=session
- Fix _clients.py docstring: 'Agent threads' → 'Agent sessions'

* Fix broken markdown links after thread→session file renames

* fix azure ai test

2026-02-12 21:00:32 +00:00

7.8 KiB

Raw Permalink Blame History

Azure OpenAI Agent Examples

This folder contains examples demonstrating different ways to create and use agents with the different Azure OpenAI chat client from the agent_framework.azure package.

Examples

File	Description
`azure_assistants_basic.py`	The simplest way to create an agent using `Agent` with `AzureOpenAIAssistantsClient`. Shows both streaming and non-streaming responses with automatic assistant creation and cleanup.
`azure_assistants_with_code_interpreter.py`	Shows how to use `AzureOpenAIAssistantsClient.get_code_interpreter_tool()` with Azure agents to write and execute Python code. Includes helper methods for accessing code interpreter data from response chunks.
`azure_assistants_with_existing_assistant.py`	Shows how to work with a pre-existing assistant by providing the assistant ID to the Azure Assistants client. Demonstrates proper cleanup of manually created assistants.
`azure_assistants_with_explicit_settings.py`	Shows how to initialize an agent with a specific assistants client, configuring settings explicitly including endpoint and deployment name.
`azure_assistants_with_function_tools.py`	Demonstrates how to use function tools with agents. Shows both agent-level tools (defined when creating the agent) and query-level tools (provided with specific queries).
`azure_assistants_with_session.py`	Demonstrates session management with Azure agents, including automatic session creation for stateless conversations and explicit session management for maintaining conversation context across multiple interactions.
`azure_chat_client_basic.py`	The simplest way to create an agent using `Agent` with `AzureOpenAIChatClient`. Shows both streaming and non-streaming responses for chat-based interactions with Azure OpenAI models.
`azure_chat_client_with_explicit_settings.py`	Shows how to initialize an agent with a specific chat client, configuring settings explicitly including endpoint and deployment name.
`azure_chat_client_with_function_tools.py`	Demonstrates how to use function tools with agents. Shows both agent-level tools (defined when creating the agent) and query-level tools (provided with specific queries).
`azure_chat_client_with_session.py`	Demonstrates session management with Azure agents, including automatic session creation for stateless conversations and explicit session management for maintaining conversation context across multiple interactions.
`azure_responses_client_basic.py`	The simplest way to create an agent using `Agent` with `AzureOpenAIResponsesClient`. Shows both streaming and non-streaming responses for structured response generation with Azure OpenAI models.
`azure_responses_client_code_interpreter_files.py`	Demonstrates using `AzureOpenAIResponsesClient.get_code_interpreter_tool()` with file uploads for data analysis. Shows how to create, upload, and analyze CSV files using Python code execution with Azure OpenAI Responses.
`azure_responses_client_image_analysis.py`	Shows how to use Azure OpenAI Responses for image analysis and vision tasks. Demonstrates multi-modal messages combining text and image content using remote URLs.
`azure_responses_client_with_code_interpreter.py`	Shows how to use `AzureOpenAIResponsesClient.get_code_interpreter_tool()` with Azure agents to write and execute Python code. Includes helper methods for accessing code interpreter data from response chunks.
`azure_responses_client_with_explicit_settings.py`	Shows how to initialize an agent with a specific responses client, configuring settings explicitly including endpoint and deployment name.
`azure_responses_client_with_file_search.py`	Demonstrates using `AzureOpenAIResponsesClient.get_file_search_tool()` with Azure OpenAI Responses Client for direct document-based question answering and information retrieval from vector stores.
`azure_responses_client_with_foundry.py`	Shows how to create an agent using an Azure AI Foundry project endpoint instead of a direct Azure OpenAI endpoint. Requires the `azure-ai-projects` package.
`azure_responses_client_with_function_tools.py`	Demonstrates how to use function tools with agents. Shows both agent-level tools (defined when creating the agent) and query-level tools (provided with specific queries).
`azure_responses_client_with_hosted_mcp.py`	Shows how to integrate Azure OpenAI Responses Client with hosted Model Context Protocol (MCP) servers using `AzureOpenAIResponsesClient.get_mcp_tool()` for extended functionality.
`azure_responses_client_with_local_mcp.py`	Shows how to integrate Azure OpenAI Responses Client with local Model Context Protocol (MCP) servers using MCPStreamableHTTPTool for extended functionality.
`azure_responses_client_with_session.py`	Demonstrates session management with Azure agents, including automatic session creation for stateless conversations and explicit session management for maintaining conversation context across multiple interactions.

Environment Variables

Make sure to set the following environment variables before running the examples:

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

For the Foundry project sample (azure_responses_client_with_foundry.py), also set:

AZURE_AI_PROJECT_ENDPOINT: Your Azure AI Foundry project endpoint

Optionally, you can set:

AZURE_OPENAI_API_VERSION: The API version to use (default is 2024-02-15-preview)
AZURE_OPENAI_API_KEY: Your Azure OpenAI API key (if not using AzureCliCredential)
AZURE_OPENAI_BASE_URL: Your Azure OpenAI base URL (if different from the endpoint)

Authentication

All examples use AzureCliCredential for authentication. Run az login in your terminal before running the examples, or replace AzureCliCredential with your preferred authentication method.

Required role-based access control (RBAC) roles

To access the Azure OpenAI API, your Azure account or service principal needs one of the following RBAC roles assigned to the Azure OpenAI resource:

Cognitive Services OpenAI User: Provides read access to Azure OpenAI resources and the ability to call the inference APIs. This is the minimum role required for running these examples.
Cognitive Services OpenAI Contributor: Provides full access to Azure OpenAI resources, including the ability to create, update, and delete deployments and models.

For most scenarios, the Cognitive Services OpenAI User role is sufficient. You can assign this role through the Azure portal under the Azure OpenAI resource's "Access control (IAM)" section.

For more detailed information about Azure OpenAI RBAC roles, see: Role-based access control for Azure OpenAI Service

7.8 KiB Raw Permalink Blame History