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

python/samples/01-get-started/03_multi_turn.py

@@ -7,10 +7,10 @@ from agent_framework.azure import AzureOpenAIResponsesClient
 from azure.identity import AzureCliCredential
 
 """
-Multi-Turn Conversations — Use AgentThread to maintain context
+Multi-Turn Conversations — Use AgentSession to maintain context
 
 This sample shows how to keep conversation history across multiple calls
-by reusing the same thread object.
+by reusing the same session object.
 
 Environment variables:
   AZURE_AI_PROJECT_ENDPOINT        — Your Azure AI Foundry project endpoint
@@ -34,15 +34,15 @@ async def main() -> None:
     # </create_agent>
 
     # <multi_turn>
-    # Create a thread to maintain conversation history
-    thread = agent.get_new_thread()
+    # Create a session to maintain conversation history
+    session = agent.create_session()
 
     # First turn
-    result = await agent.run("My name is Alice and I love hiking.", thread=thread)
+    result = await agent.run("My name is Alice and I love hiking.", session=session)
     print(f"Agent: {result}\n")
 
     # Second turn — the agent should remember the user's name and hobby
-    result = await agent.run("What do you remember about me?", thread=thread)
+    result = await agent.run("What do you remember about me?", session=session)
     print(f"Agent: {result}")
     # </multi_turn>
 

python/samples/01-get-started/04_memory.py

@@ -2,10 +2,9 @@
 
 import asyncio
 import os
-from collections.abc import MutableSequence
 from typing import Any
 
-from agent_framework import Context, ContextProvider, Message
+from agent_framework._sessions import AgentSession, BaseContextProvider, SessionContext
 from agent_framework.azure import AzureOpenAIResponsesClient
 from azure.identity import AzureCliCredential
 
@@ -23,28 +22,37 @@ Environment variables:
 
 
 # <context_provider>
-class UserNameProvider(ContextProvider):
+class UserNameProvider(BaseContextProvider):
     """A simple context provider that remembers the user's name."""
 
     def __init__(self) -> None:
+        super().__init__(source_id="user-name-provider")
         self.user_name: str | None = None
 
-    async def invoking(self, messages: Message | MutableSequence[Message], **kwargs: Any) -> Context:
+    async def before_run(
+        self,
+        *,
+        agent: Any,
+        session: AgentSession,
+        context: SessionContext,
+        state: dict[str, Any],
+    ) -> None:
         """Called before each agent invocation — add extra instructions."""
         if self.user_name:
-            return Context(instructions=f"The user's name is {self.user_name}. Always address them by name.")
-        return Context(instructions="You don't know the user's name yet. Ask for it politely.")
+            context.instructions.append(f"The user's name is {self.user_name}. Always address them by name.")
+        else:
+            context.instructions.append("You don't know the user's name yet. Ask for it politely.")
 
-    async def invoked(
+    async def after_run(
         self,
-        request_messages: Message | list[Message] | None = None,
-        response_messages: "Message | list[Message] | None" = None,
-        invoke_exception: Exception | None = None,
-        **kwargs: Any,
+        *,
+        agent: Any,
+        session: AgentSession,
+        context: SessionContext,
+        state: dict[str, Any],
     ) -> None:
         """Called after each agent invocation — extract information."""
-        msgs = [request_messages] if isinstance(request_messages, Message) else list(request_messages or [])
-        for msg in msgs:
+        for msg in context.input_messages:
             text = msg.text if hasattr(msg, "text") else ""
             if isinstance(text, str) and "my name is" in text.lower():
                 # Simple extraction — production code should use structured extraction
@@ -66,22 +74,22 @@ async def main() -> None:
     agent = client.as_agent(
         name="MemoryAgent",
         instructions="You are a friendly assistant.",
-        context_provider=memory,
+        context_providers=[memory],
     )
     # </create_agent>
 
-    thread = agent.get_new_thread()
+    session = agent.create_session()
 
     # The provider doesn't know the user yet — it will ask for a name
-    result = await agent.run("Hello! What's the square root of 9?", thread=thread)
+    result = await agent.run("Hello! What's the square root of 9?", session=session)
     print(f"Agent: {result}\n")
 
     # Now provide the name — the provider extracts and stores it
-    result = await agent.run("My name is Alice", thread=thread)
+    result = await agent.run("My name is Alice", session=session)
     print(f"Agent: {result}\n")
 
     # Subsequent calls are personalized
-    result = await agent.run("What is 2 + 2?", thread=thread)
+    result = await agent.run("What is 2 + 2?", session=session)
     print(f"Agent: {result}\n")
 
     print(f"[Memory] Stored user name: {memory.user_name}")