mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
Eduard van Valkenburg
1e350ea22f
* 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
5.5 KiB
5.5 KiB
Semantic Kernel → Microsoft Agent Framework Migration Samples
This gallery helps Semantic Kernel (SK) developers move to the Microsoft Agent Framework (AF) with minimal guesswork. Each script pairs SK code with its AF equivalent so you can compare primitives, tooling, and orchestration patterns side by side while you migrate production workloads.
What’s Included
What’s Included
Chat completion parity
- 01_basic_chat_completion.py — Minimal SK
ChatCompletionAgentand AFAgentconversation. - 02_chat_completion_with_tool.py — Adds a simple tool/function call in both SDKs.
- 03_chat_completion_thread_and_stream.py — Demonstrates session reuse and streaming prompts.
Azure AI agent parity
- 01_basic_azure_ai_agent.py — Create and run an Azure AI agent end to end.
- 02_azure_ai_agent_with_code_interpreter.py — Enable hosted code interpreter/tool execution.
- 03_azure_ai_agent_threads_and_followups.py — Persist sessions and follow-ups across invocations.
OpenAI Assistants API parity
- 01_basic_openai_assistant.py — Baseline assistant comparison.
- 02_openai_assistant_with_code_interpreter.py — Code interpreter tool usage.
- 03_openai_assistant_function_tool.py — Custom function tooling.
OpenAI Responses API parity
- 01_basic_responses_agent.py — Basic responses agent migration.
- 02_responses_agent_with_tool.py — Tool-augmented responses workflows.
- 03_responses_agent_structured_output.py — Structured JSON output alignment.
Copilot Studio parity
- 01_basic_copilot_studio_agent.py — Minimal Copilot Studio agent invocation.
- 02_copilot_studio_streaming.py — Streaming responses from Copilot Studio agents.
Orchestrations
- sequential.py — Step-by-step SK Team → AF
SequentialBuildermigration. - concurrent_basic.py — Concurrent orchestration parity.
- group_chat.py — Group chat coordination with an LLM-backed manager in both SDKs.
- handoff.py - Handoff coordination between agents.
- magentic.py — Magentic Team orchestration vs. AF builder wiring.
Processes
- fan_out_fan_in_process.py — Fan-out/fan-in comparison between SK Process Framework and AF workflows.
- nested_process.py — Nested process orchestration vs. AF sub-workflows.
Each script is fully async and the main() routine runs both implementations back to back so you can observe their outputs in a single execution.
Prerequisites
- Python 3.10 or later.
- Access to the necessary model endpoints (Azure OpenAI, OpenAI, Azure AI, Copilot Studio, etc.).
- Installed SDKs:
semantic-kerneland the Microsoft Agent Framework (pip install semantic-kernel agent-framework), or the repo’s editable packages if you are developing locally. - Service credentials exposed through environment variables (for example
OPENAI_API_KEY,AZURE_OPENAI_ENDPOINT,AZURE_OPENAI_KEY, or Copilot Studio auth settings).
Running Single-Agent Samples
From the repository root:
python samples/semantic-kernel-migration/chat_completion/01_basic_chat_completion.py
Every script accepts no CLI arguments and will first call the SK implementation, followed by the AF version. Adjust the prompt or credentials inside the file as necessary before running.
Running Orchestration & Workflow Samples
Advanced comparisons are split between samantic-kernel-migration/orchestrations (Sequential, Concurrent, Magentic) and samantic-kernel-migration/processes (fan-out/fan-in, nested). You can run them directly, or isolate dependencies in a throwaway virtual environment:
cd samples/semantic-kernel-migration
uv venv --python 3.10 .venv-migration
source .venv-migration/bin/activate
uv pip install semantic-kernel agent-framework
uv run python orchestrations/sequential.py
uv run python processes/fan_out_fan_in_process.py
Swap the script path for any other workflow or process sample. Deactivate the sandbox with deactivate when you are finished.
Tips for Migration
- Keep the original SK sample open while iterating on the AF equivalent; the code is intentionally formatted so you can copy/paste across SDKs.
- Sessions/conversation state are explicit in AF. When porting SK code that relies on implicit session reuse, call
agent.create_session()and pass it into eachruncall. - Tools map cleanly: SK
@kernel_functionplugins translate to AF@toolcallables. Hosted tools (code interpreter, web search, MCP) are available only in AF—introduce them once parity is achieved. - For multi-agent orchestration, AF workflows expose checkpoints and resume capabilities that SK Process/Team abstractions do not. Use the workflow samples as a blueprint when modernizing complex agent graphs.