Merge branch 'main' into feat/durable_task

.github/actions/python-setup/action.yml

@@ -8,6 +8,10 @@ inputs:
     os:
       description: The operating system to set up
       required: true
+    exclude-packages:
+      description: Space-separated list of packages to exclude from uv sync
+      required: false
+      default: ''
 
 runs:
     using: "composite"
@@ -19,6 +23,20 @@ runs:
             enable-cache: true
             cache-suffix: ${{ inputs.os }}-${{ inputs.python-version }}
             cache-dependency-glob: "**/uv.lock"
+      - name: Exclude incompatible workspace packages
+        if: ${{ inputs.exclude-packages != '' }}
+        shell: bash
+        run: |
+          for pkg in ${{ inputs.exclude-packages }}; do
+            for f in python/packages/*/pyproject.toml; do
+              if grep -q "name = \"$pkg\"" "$f"; then
+                pkg_dir=$(dirname "$f" | sed 's|python/||')
+                echo "Excluding workspace package: $pkg ($pkg_dir)"
+                sed -i.bak '/\[tool\.uv\.workspace\]/a\exclude = ["'"$pkg_dir"'"]' python/pyproject.toml
+                sed -i.bak '/'"$pkg"' = { workspace = true }/d' python/pyproject.toml
+              fi
+            done
+          done
       - name: Install the project
         shell: bash
         run: |

.github/workflows/python-code-quality.yml

@@ -18,7 +18,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.10"]
+        python-version: ["3.11"]
     runs-on: ubuntu-latest
     continue-on-error: true
     defaults:
@@ -55,7 +55,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.10"]
+        python-version: ["3.11"]
     runs-on: ubuntu-latest
     continue-on-error: true
     defaults:
@@ -84,7 +84,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.10"]
+        python-version: ["3.11"]
     runs-on: ubuntu-latest
     continue-on-error: true
     defaults:
@@ -117,7 +117,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.10"]
+        python-version: ["3.11"]
     runs-on: ubuntu-latest
     continue-on-error: true
     defaults:

.github/workflows/python-integration-tests.yml

@@ -170,7 +170,7 @@ jobs:
     environment: integration
     timeout-minutes: 60
     env:
-      UV_PYTHON: "3.10"
+      UV_PYTHON: "3.11"
       OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
       OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
       OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}

.github/workflows/python-lab-tests.yml

@@ -67,6 +67,7 @@ jobs:
         with:
           python-version: ${{ matrix.python-version }}
           os: ${{ runner.os }}
+          exclude-packages: ${{ matrix.python-version == '3.10' && 'agent-framework-github-copilot' || '' }}
         env:
           # Configure a constant location for the uv cache
           UV_CACHE_DIR: /tmp/.uv-cache

.github/workflows/python-merge-tests.yml

@@ -288,7 +288,7 @@ jobs:
     runs-on: ubuntu-latest
     environment: integration
     env:
-      UV_PYTHON: "3.10"
+      UV_PYTHON: "3.11"
       OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
       OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
       OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}

.github/workflows/python-test-coverage.yml

@@ -20,7 +20,7 @@ jobs:
       run:
         working-directory: python
     env:
-      UV_PYTHON: "3.10"
+      UV_PYTHON: "3.11"
     steps:
       - uses: actions/checkout@v6
       # Save the PR number to a file since the workflow_run event

.github/workflows/python-tests.yml

@@ -34,12 +34,13 @@ jobs:
         with:
           python-version: ${{ matrix.python-version }}
           os: ${{ runner.os }}
+          exclude-packages: ${{ matrix.python-version == '3.10' && 'agent-framework-github-copilot' || '' }}
         env:
           # Configure a constant location for the uv cache
           UV_CACHE_DIR: /tmp/.uv-cache
       # Unit tests
       - name: Run all tests
-        run: uv run poe all-tests
+        run: uv run poe all-tests ${{ matrix.python-version == '3.10' && '--ignore-glob=packages/github_copilot/**' || '' }}
         working-directory: ./python
 
       # Surface failing tests

python/AGENTS.md

@@ -20,6 +20,13 @@ When making changes to a package, check if the following need updates:
 - The package's `AGENTS.md` file (adding/removing/renaming public APIs, architecture changes, import path changes)
 - The agent skills in `.github/skills/` if conventions, commands, or workflows change
 
+## Pull Request Description Guidance
+
+When preparing a PR description:
+- Follow the repository PR template at `.github/pull_request_template.md` and keep its structure/headings.
+- Describe the net change relative to `main` (this is implied; do not call it out explicitly as "vs main").
+- Do not add ad-hoc validation sections (for example, "Validation" or "Tests run"); CI/CD and the template checklist cover validation status.
+
 ## Quick Reference
 
 Run `uv run poe` from the `python/` directory to see available commands. See [DEV_SETUP.md](DEV_SETUP.md) for detailed usage.

python/packages/azure-ai/agent_framework_azure_ai/_client.py

@@ -37,9 +37,8 @@ from agent_framework.openai._responses_client import RawOpenAIResponsesClient
 from azure.ai.projects.aio import AIProjectClient
 from azure.ai.projects.models import (
     ApproximateLocation,
-    CodeInterpreterContainerAuto,
+    AutoCodeInterpreterToolParam,
     CodeInterpreterTool,
-    FoundryFeaturesOptInKeys,
     ImageGenTool,
     MCPTool,
     PromptAgentDefinition,
@@ -66,7 +65,6 @@ if sys.version_info >= (3, 11):
 else:
     from typing_extensions import Self, TypedDict  # type: ignore # pragma: no cover
 
-
 logger = logging.getLogger("agent_framework.azure")
 
 
@@ -79,9 +77,6 @@ class AzureAIProjectAgentOptions(OpenAIResponsesOptions, total=False):
     reasoning: Reasoning  # type: ignore[misc]
     """Configuration for enabling reasoning capabilities (requires azure.ai.projects.models.Reasoning)."""
 
-    foundry_features: FoundryFeaturesOptInKeys | str
-    """Optional Foundry preview feature opt-in for agent version creation."""
-
 
 AzureAIClientOptionsT = TypeVar(
     "AzureAIClientOptionsT",
@@ -123,6 +118,7 @@ class RawAzureAIClient(RawOpenAIResponsesClient[AzureAIClientOptionsT], Generic[
         model_deployment_name: str | None = None,
         credential: AzureCredentialTypes | None = None,
         use_latest_version: bool | None = None,
+        allow_preview: bool | None = None,
         env_file_path: str | None = None,
         env_file_encoding: str | None = None,
         **kwargs: Any,
@@ -148,6 +144,7 @@ class RawAzureAIClient(RawOpenAIResponsesClient[AzureAIClientOptionsT], Generic[
                 AsyncTokenCredential, or a callable token provider.
             use_latest_version: Boolean flag that indicates whether to use latest agent version
                 if it exists in the service.
+            allow_preview: Enables preview opt-in on internally-created ``AIProjectClient``.
             env_file_path: Path to environment file for loading settings.
             env_file_encoding: Encoding of the environment file.
             kwargs: Additional keyword arguments passed to the parent class.
@@ -208,11 +205,14 @@ class RawAzureAIClient(RawOpenAIResponsesClient[AzureAIClientOptionsT], Generic[
             # Use provided credential
             if not credential:
                 raise ValueError("Azure credential is required when project_client is not provided.")
-            project_client = AIProjectClient(
+            project_client_kwargs: dict[str, Any] = {
-                endpoint=resolved_endpoint,
+                "endpoint": resolved_endpoint,
-                credential=credential,  # type: ignore[arg-type]
+                "credential": credential,  # type: ignore[arg-type]
-                user_agent=AGENT_FRAMEWORK_USER_AGENT,
+                "user_agent": AGENT_FRAMEWORK_USER_AGENT,
-            )
+            }
+            if allow_preview is not None:
+                project_client_kwargs["allow_preview"] = allow_preview
+            project_client = AIProjectClient(**project_client_kwargs)
             should_close_client = True
 
         # Initialize parent
@@ -413,8 +413,6 @@ class RawAzureAIClient(RawOpenAIResponsesClient[AzureAIClientOptionsT], Generic[
                 "definition": PromptAgentDefinition(**args),
                 "description": self.agent_description,
             }
-            if foundry_features := run_options.get("foundry_features"):
-                create_version_kwargs["foundry_features"] = foundry_features
 
             created_agent = await self.project_client.agents.create_version(**create_version_kwargs)
 
@@ -513,7 +511,7 @@ class RawAzureAIClient(RawOpenAIResponsesClient[AzureAIClientOptionsT], Generic[
             "temperature": ("temperature",),
             "top_p": ("top_p",),
             "reasoning": ("reasoning",),
-            "foundry_features": ("foundry_features",),
+            "allow_preview": ("allow_preview",),
         }
 
         for run_keys in agent_level_option_to_run_keys.values():
@@ -939,7 +937,7 @@ class RawAzureAIClient(RawOpenAIResponsesClient[AzureAIClientOptionsT], Generic[
         if file_ids is None and isinstance(container, dict):
             file_ids = container.get("file_ids")
         resolved = resolve_file_ids(file_ids)
-        tool_container = CodeInterpreterContainerAuto(file_ids=resolved)
+        tool_container = AutoCodeInterpreterToolParam(file_ids=resolved)
         return CodeInterpreterTool(container=tool_container, **kwargs)
 
     @staticmethod
@@ -1244,6 +1242,7 @@ class AzureAIClient(
         model_deployment_name: str | None = None,
         credential: AzureCredentialTypes | None = None,
         use_latest_version: bool | None = None,
+        allow_preview: bool | None = None,
         middleware: Sequence[ChatAndFunctionMiddlewareTypes] | None = None,
         function_invocation_configuration: FunctionInvocationConfiguration | None = None,
         env_file_path: str | None = None,
@@ -1268,6 +1267,7 @@ class AzureAIClient(
                 or AsyncTokenCredential.
             use_latest_version: Boolean flag that indicates whether to use latest agent version
                 if it exists in the service.
+            allow_preview: Enables preview opt-in on internally-created ``AIProjectClient``
             middleware: Optional sequence of chat middlewares to include.
             function_invocation_configuration: Optional function invocation configuration.
             env_file_path: Path to environment file for loading settings.
@@ -1318,6 +1318,7 @@ class AzureAIClient(
             model_deployment_name=model_deployment_name,
             credential=credential,
             use_latest_version=use_latest_version,
+            allow_preview=allow_preview,
             middleware=middleware,
             function_invocation_configuration=function_invocation_configuration,
             env_file_path=env_file_path,

python/packages/azure-ai/agent_framework_azure_ai/_foundry_memory_provider.py

@@ -18,6 +18,7 @@ from agent_framework._sessions import AgentSession, BaseContextProvider, Session
 from agent_framework._settings import load_settings
 from agent_framework.azure._entra_id_authentication import AzureCredentialTypes
 from azure.ai.projects.aio import AIProjectClient
+from openai.types.responses import ResponseInputItemParam
 
 from ._shared import AzureAISettings
 
@@ -58,6 +59,7 @@ class FoundryMemoryProvider(BaseContextProvider):
         project_client: AIProjectClient | None = None,
         project_endpoint: str | None = None,
         credential: AzureCredentialTypes | None = None,
+        allow_preview: bool | None = None,
         memory_store_name: str,
         scope: str | None = None,
         context_prompt: str | None = None,
@@ -74,6 +76,7 @@ class FoundryMemoryProvider(BaseContextProvider):
             credential: Azure credential for authentication. Accepts a TokenCredential,
                 AsyncTokenCredential, or a callable token provider.
                 Required when project_client is not provided.
+            allow_preview: Enables preview opt-in on internally-created ``AIProjectClient``.
             memory_store_name: The name of the memory store to use.
             scope: The namespace that logically groups and isolates memories (e.g., user ID).
                 If None, `session_id` will be used.
@@ -100,11 +103,14 @@ class FoundryMemoryProvider(BaseContextProvider):
                 )
             if not credential:
                 raise ValueError("Azure credential is required when project_client is not provided.")
-            project_client = AIProjectClient(
+            project_client_kwargs: dict[str, Any] = {
-                endpoint=resolved_endpoint,
+                "endpoint": resolved_endpoint,
-                credential=credential,  # type: ignore[arg-type]
+                "credential": credential,  # type: ignore[arg-type]
-                user_agent=AGENT_FRAMEWORK_USER_AGENT,
+                "user_agent": AGENT_FRAMEWORK_USER_AGENT,
-            )
+            }
+            if allow_preview is not None:
+                project_client_kwargs["allow_preview"] = allow_preview
+            project_client = AIProjectClient(**project_client_kwargs)
 
         if not memory_store_name:
             raise ValueError("memory_store_name is required")
@@ -169,8 +175,8 @@ class FoundryMemoryProvider(BaseContextProvider):
             return
 
         # Convert input messages to memory search item format
-        items = [
+        items: list[ResponseInputItemParam] = [
-            {"type": "text", "text": msg.text}
+            {"type": "message", "role": "user", "content": msg.text}
             for msg in context.input_messages
             if msg and msg.text and msg.text.strip()
         ]
@@ -224,7 +230,7 @@ class FoundryMemoryProvider(BaseContextProvider):
             messages_to_store.extend(context.response.messages)
 
         # Filter and convert messages to memory update item format
-        items: list[dict[str, str]] = []
+        items: list[ResponseInputItemParam] = []
         for message in messages_to_store:
             if message.role in {"user", "assistant", "system"} and message.text and message.text.strip():
                 if message.role == "user":

python/packages/azure-ai/agent_framework_azure_ai/_project_provider.py

@@ -102,6 +102,7 @@ class AzureAIProjectAgentProvider(Generic[OptionsCoT]):
         project_endpoint: str | None = None,
         model: str | None = None,
         credential: AzureCredentialTypes | None = None,
+        allow_preview: bool | None = None,
         env_file_path: str | None = None,
         env_file_encoding: str | None = None,
     ) -> None:
@@ -117,6 +118,7 @@ class AzureAIProjectAgentProvider(Generic[OptionsCoT]):
             credential: Azure credential for authentication. Accepts a TokenCredential,
                 AsyncTokenCredential, or a callable token provider.
                 Required when project_client is not provided.
+            allow_preview: Enables preview opt-in on internally-created ``AIProjectClient``.
             env_file_path: Path to environment file for loading settings.
             env_file_encoding: Encoding of the environment file.
 
@@ -146,11 +148,14 @@ class AzureAIProjectAgentProvider(Generic[OptionsCoT]):
             if not credential:
                 raise ValueError("Azure credential is required when project_client is not provided.")
 
-            project_client = AIProjectClient(
+            project_client_kwargs: dict[str, Any] = {
-                endpoint=resolved_endpoint,
+                "endpoint": resolved_endpoint,
-                credential=credential,  # type: ignore[arg-type]
+                "credential": credential,  # type: ignore[arg-type]
-                user_agent=AGENT_FRAMEWORK_USER_AGENT,
+                "user_agent": AGENT_FRAMEWORK_USER_AGENT,
-            )
+            }
+            if allow_preview is not None:
+                project_client_kwargs["allow_preview"] = allow_preview
+            project_client = AIProjectClient(**project_client_kwargs)
             self._should_close_client = True
 
         self._project_client = project_client
@@ -199,7 +204,6 @@ class AzureAIProjectAgentProvider(Generic[OptionsCoT]):
         response_format = opts.get("response_format")
         rai_config = opts.get("rai_config")
         reasoning = opts.get("reasoning")
-        foundry_features = opts.get("foundry_features")
 
         args: dict[str, Any] = {"model": resolved_model}
 
@@ -246,8 +250,6 @@ class AzureAIProjectAgentProvider(Generic[OptionsCoT]):
             "definition": PromptAgentDefinition(**args),
             "description": description,
         }
-        if foundry_features:
-            create_version_kwargs["foundry_features"] = foundry_features
 
         created_agent = await self._project_client.agents.create_version(**create_version_kwargs)
 

python/packages/azure-ai/agent_framework_azure_ai/_shared.py

@@ -19,9 +19,9 @@ from azure.ai.agents.models import (
 from azure.ai.projects.models import (
     CodeInterpreterTool,
     MCPTool,
-    TextResponseFormatConfigurationResponseFormatJsonObject,
+    TextResponseFormatJsonObject,
-    TextResponseFormatConfigurationResponseFormatText,
     TextResponseFormatJsonSchema,
+    TextResponseFormatText,
     Tool,
     WebSearchPreviewTool,
 )
@@ -479,11 +479,7 @@ def _prepare_mcp_tool_dict_for_azure_ai(tool_dict: dict[str, Any]) -> MCPTool:
 
 def create_text_format_config(
     response_format: type[BaseModel] | Mapping[str, Any],
-) -> (
+) -> TextResponseFormatJsonSchema | TextResponseFormatJsonObject | TextResponseFormatText:
-    TextResponseFormatJsonSchema
-    | TextResponseFormatConfigurationResponseFormatJsonObject
-    | TextResponseFormatConfigurationResponseFormatText
-):
     """Convert response_format into Azure text format configuration."""
     if isinstance(response_format, type) and issubclass(response_format, BaseModel):
         schema = response_format.model_json_schema()
@@ -513,9 +509,9 @@ def create_text_format_config(
                 config_kwargs["description"] = format_config["description"]
             return TextResponseFormatJsonSchema(**config_kwargs)
         if format_type == "json_object":
-            return TextResponseFormatConfigurationResponseFormatJsonObject()
+            return TextResponseFormatJsonObject()
         if format_type == "text":
-            return TextResponseFormatConfigurationResponseFormatText()
+            return TextResponseFormatText()
 
     raise IntegrationInvalidRequestException("response_format must be a Pydantic model or mapping.")
 

python/packages/azure-ai/tests/test_azure_ai_client.py

@@ -28,7 +28,7 @@ from agent_framework.openai._responses_client import RawOpenAIResponsesClient
 from azure.ai.projects.aio import AIProjectClient
 from azure.ai.projects.models import (
     ApproximateLocation,
-    CodeInterpreterContainerAuto,
+    AutoCodeInterpreterToolParam,
     CodeInterpreterTool,
     FileSearchTool,
     ImageGenTool,
@@ -1296,7 +1296,7 @@ def test_from_azure_ai_tools_mcp() -> None:
 
 def test_from_azure_ai_tools_code_interpreter() -> None:
     """Test from_azure_ai_tools with Code Interpreter tool."""
-    ci_tool = CodeInterpreterTool(container=CodeInterpreterContainerAuto(file_ids=["file-1"]))
+    ci_tool = CodeInterpreterTool(container=AutoCodeInterpreterToolParam(file_ids=["file-1"]))
     parsed_tools = from_azure_ai_tools([ci_tool])
     assert len(parsed_tools) == 1
     assert parsed_tools[0]["type"] == "code_interpreter"

python/packages/azure-ai/tests/test_foundry_memory_provider.py

@@ -86,6 +86,7 @@ class TestInit:
             provider = FoundryMemoryProvider(
                 project_endpoint="https://test.project.endpoint",
                 credential=mock_credential,  # type: ignore[arg-type]
+                allow_preview=True,
                 memory_store_name="test_store",
                 scope="user_123",
             )
@@ -93,6 +94,7 @@ class TestInit:
             mock_ai_project_client.assert_called_once_with(
                 endpoint="https://test.project.endpoint",
                 credential=mock_credential,
+                allow_preview=True,
                 user_agent=AGENT_FRAMEWORK_USER_AGENT,
             )
 

python/packages/core/agent_framework/_skills.py

@@ -112,9 +112,7 @@ class SkillResource:
         self._accepts_kwargs: bool = False
         if function is not None:
             sig = inspect.signature(function)
-            self._accepts_kwargs = any(
+            self._accepts_kwargs = any(p.kind == inspect.Parameter.VAR_KEYWORD for p in sig.parameters.values())
-                p.kind == inspect.Parameter.VAR_KEYWORD for p in sig.parameters.values()
-            )
 
 
 class Skill:

python/packages/core/agent_framework/_tools.py

@@ -1458,7 +1458,7 @@ def _update_conversation_id(
     if conversation_id is None:
         return
     if "chat_options" in kwargs:
-        kwargs["chat_options"].conversation_id = conversation_id
+        kwargs["chat_options"]["conversation_id"] = conversation_id
     else:
         kwargs["conversation_id"] = conversation_id
 

python/packages/core/agent_framework/azure/_responses_client.py

@@ -73,6 +73,7 @@ class AzureOpenAIResponsesClient(  # type: ignore[misc]
         async_client: AsyncOpenAI | None = None,
         project_client: Any | None = None,
         project_endpoint: str | None = None,
+        allow_preview: bool | None = None,
         env_file_path: str | None = None,
         env_file_encoding: str | None = None,
         instruction_role: str | None = None,
@@ -120,6 +121,7 @@ class AzureOpenAIResponsesClient(  # type: ignore[misc]
             project_endpoint: The Azure AI Foundry project endpoint URL.
                 When provided with ``credential``, an ``AIProjectClient`` will be created
                 and used to obtain the OpenAI client. Requires the ``azure-ai-projects`` package.
+            allow_preview: Enables preview opt-in on internally-created ``AIProjectClient``.
             env_file_path: Use the environment settings file as a fallback to using env vars.
             env_file_encoding: The encoding of the environment settings file, defaults to 'utf-8'.
             instruction_role: The role to use for 'instruction' messages, for example, summarization
@@ -189,6 +191,7 @@ class AzureOpenAIResponsesClient(  # type: ignore[misc]
                 project_client=project_client,
                 project_endpoint=project_endpoint,
                 credential=credential,
+                allow_preview=allow_preview,
             )
 
         azure_openai_settings = load_settings(
@@ -246,21 +249,9 @@ class AzureOpenAIResponsesClient(  # type: ignore[misc]
         project_client: AIProjectClient | None,
         project_endpoint: str | None,
         credential: AzureCredentialTypes | AzureTokenProvider | None,
+        allow_preview: bool | None = None,
     ) -> AsyncOpenAI:
-        """Create an AsyncOpenAI client from an Azure AI Foundry project.
+        """Create an AsyncOpenAI client from an Azure AI Foundry project."""
-
-        Args:
-            project_client: An existing AIProjectClient to use.
-            project_endpoint: The Azure AI Foundry project endpoint URL.
-            credential: Azure credential for authentication.
-
-        Returns:
-            An AsyncAzureOpenAI client obtained from the project client.
-
-        Raises:
-            ValueError: If required parameters are missing or
-                the azure-ai-projects package is not installed.
-        """
         if project_client is not None:
             return project_client.get_openai_client()
 
@@ -268,11 +259,14 @@ class AzureOpenAIResponsesClient(  # type: ignore[misc]
             raise ValueError("Azure AI project endpoint is required when project_client is not provided.")
         if not credential:
             raise ValueError("Azure credential is required when using project_endpoint without a project_client.")
-        project_client = AIProjectClient(
+        project_client_kwargs: dict[str, Any] = {
-            endpoint=project_endpoint,
+            "endpoint": project_endpoint,
-            credential=credential,  # type: ignore[arg-type]
+            "credential": credential,  # type: ignore[arg-type]
-            user_agent=AGENT_FRAMEWORK_USER_AGENT,
+            "user_agent": AGENT_FRAMEWORK_USER_AGENT,
-        )
+        }
+        if allow_preview is not None:
+            project_client_kwargs["allow_preview"] = allow_preview
+        project_client = AIProjectClient(**project_client_kwargs)
         return project_client.get_openai_client()
 
     @override

python/packages/core/agent_framework/openai/_chat_client.py

@@ -327,7 +327,9 @@ class RawOpenAIChatClient(  # type: ignore[misc]
             messages = prepend_instructions_to_messages(list(messages), instructions, role="system")
 
         # Start with a copy of options
-        run_options = {k: v for k, v in options.items() if v is not None and k not in {"instructions", "tools"}}
+        run_options = {
+            k: v for k, v in options.items() if v is not None and k not in {"instructions", "tools", "conversation_id"}
+        }
 
         # messages
         if messages and "messages" not in run_options:

python/packages/core/pyproject.toml

@@ -34,7 +34,7 @@ dependencies = [
     # connectors and functions
     "openai>=1.99.0",
     "azure-identity>=1,<2",
-    "azure-ai-projects == 2.0.0b4",
+    "azure-ai-projects>=2.0.0,<3.0",
     "mcp[ws]>=1.24.0,<2",
     "packaging>=24.1",
 ]
@@ -55,7 +55,7 @@ all = [
     "agent-framework-devui",
     "agent-framework-durabletask",
     "agent-framework-foundry-local",
-    "agent-framework-github-copilot",
+    "agent-framework-github-copilot; python_version >= '3.11'",
     "agent-framework-lab",
     "agent-framework-mem0",
     "agent-framework-ollama",

python/packages/core/tests/azure/test_azure_chat_client.py

@@ -626,6 +626,73 @@ async def test_streaming_with_none_delta(
     assert any(msg.contents for msg in results)
 
 
+@patch.object(AsyncChatCompletions, "create", new_callable=AsyncMock)
+async def test_cmc_with_conversation_id(
+    mock_create: AsyncMock,
+    azure_openai_unit_test_env: dict[str, str],
+    chat_history: list[Message],
+    mock_chat_completion_response: ChatCompletion,
+) -> None:
+    """Test that conversation_id is excluded from the completions create call."""
+    mock_create.return_value = mock_chat_completion_response
+    chat_history.append(Message(text="hello world", role="user"))
+
+    azure_chat_client = AzureOpenAIChatClient()
+    await azure_chat_client.get_response(
+        messages=chat_history,
+        options={"conversation_id": "12345"},
+    )
+
+    call_kwargs = mock_create.call_args.kwargs
+    assert "conversation_id" not in call_kwargs
+
+
+@patch.object(AsyncChatCompletions, "create", new_callable=AsyncMock)
+async def test_cmc_streaming_with_conversation_id(
+    mock_create: AsyncMock,
+    azure_openai_unit_test_env: dict[str, str],
+    chat_history: list[Message],
+    mock_streaming_chat_completion_response: AsyncStream[ChatCompletionChunk],
+) -> None:
+    """Test that conversation_id is excluded from the streaming completions create call."""
+    mock_create.return_value = mock_streaming_chat_completion_response
+    chat_history.append(Message(text="hello world", role="user"))
+
+    azure_chat_client = AzureOpenAIChatClient()
+    async for _ in azure_chat_client.get_response(
+        messages=chat_history,
+        options={"conversation_id": "12345"},
+        stream=True,
+    ):
+        pass
+
+    call_kwargs = mock_create.call_args.kwargs
+    assert "conversation_id" not in call_kwargs
+
+
+@patch.object(AsyncChatCompletions, "create", new_callable=AsyncMock)
+async def test_cmc_agent_with_service_session_id(
+    mock_create: AsyncMock,
+    azure_openai_unit_test_env: dict[str, str],
+    mock_chat_completion_response: ChatCompletion,
+) -> None:
+    """Test that agent.run() with a session containing service_session_id works correctly."""
+    mock_create.return_value = mock_chat_completion_response
+
+    azure_chat_client = AzureOpenAIChatClient()
+    agent = azure_chat_client.as_agent(
+        name="TestAgent",
+        instructions="You are a helpful assistant.",
+    )
+
+    session = agent.get_session(service_session_id="12345")
+    response = await agent.run("hello", session=session)
+
+    assert response is not None
+    call_kwargs = mock_create.call_args.kwargs
+    assert "conversation_id" not in call_kwargs
+
+
 @tool(approval_mode="never_require")
 def get_story_text() -> str:
     """Returns a story about Emily and David."""

python/packages/core/tests/core/test_function_invocation_logic.py

@@ -3449,3 +3449,66 @@ async def test_streaming_function_calling_response_includes_reasoning_and_tool_r
     reasoning_contents = [c for msg in response.messages for c in msg.contents if c.type == "text_reasoning"]
     assert len(reasoning_contents) >= 1
     assert reasoning_contents[0].id == "rs_test123"
+
+
+# region _update_conversation_id unit tests
+
+
+class TestUpdateConversationId:
+    """Tests for _update_conversation_id handling dict chat_options."""
+
+    def test_chat_options_as_dict(self):
+        """When chat_options is a plain dict, conversation_id should be set via key access."""
+        from agent_framework._tools import _update_conversation_id
+
+        kwargs: dict[str, Any] = {"chat_options": {}}
+        _update_conversation_id(kwargs, "conv_1")
+        assert kwargs["chat_options"]["conversation_id"] == "conv_1"
+
+    def test_chat_options_as_typed_dict(self):
+        """When chat_options is a ChatOptions TypedDict, conversation_id should be set via key access."""
+        from agent_framework import ChatOptions
+        from agent_framework._tools import _update_conversation_id
+
+        opts: ChatOptions = {"temperature": 0.5}
+        kwargs: dict[str, Any] = {"chat_options": opts}
+        _update_conversation_id(kwargs, "conv_2")
+        assert kwargs["chat_options"]["conversation_id"] == "conv_2"
+
+    def test_no_chat_options_falls_back_to_kwargs(self):
+        """When chat_options is absent, conversation_id should be set directly on kwargs."""
+        from agent_framework._tools import _update_conversation_id
+
+        kwargs: dict[str, Any] = {}
+        _update_conversation_id(kwargs, "conv_4")
+        assert kwargs["conversation_id"] == "conv_4"
+
+    def test_none_conversation_id_is_noop(self):
+        """When conversation_id is None, kwargs should not be modified."""
+        from agent_framework._tools import _update_conversation_id
+
+        kwargs: dict[str, Any] = {"chat_options": {}}
+        _update_conversation_id(kwargs, None)
+        assert "conversation_id" not in kwargs["chat_options"]
+        assert "conversation_id" not in kwargs
+
+    def test_options_dict_also_updated(self):
+        """The optional options dict should also receive conversation_id."""
+        from agent_framework._tools import _update_conversation_id
+
+        kwargs: dict[str, Any] = {"chat_options": {}}
+        options: dict[str, Any] = {}
+        _update_conversation_id(kwargs, "conv_5", options)
+        assert kwargs["chat_options"]["conversation_id"] == "conv_5"
+        assert options["conversation_id"] == "conv_5"
+
+    def test_dict_overwrites_existing_conversation_id(self):
+        """When a dict already has a conversation_id, it should be overwritten."""
+        from agent_framework._tools import _update_conversation_id
+
+        kwargs: dict[str, Any] = {"chat_options": {"conversation_id": "old_id"}}
+        _update_conversation_id(kwargs, "new_id")
+        assert kwargs["chat_options"]["conversation_id"] == "new_id"
+
+
+# endregion

python/packages/core/tests/openai/test_openai_chat_client.py

@@ -1161,6 +1161,21 @@ def test_prepare_options_removes_parallel_tool_calls_when_no_tools(openai_unit_t
     assert "parallel_tool_calls" not in prepared_options
 
 
+def test_prepare_options_excludes_conversation_id(openai_unit_test_env: dict[str, str]) -> None:
+    """Test that conversation_id is excluded from prepared options for chat completions."""
+    client = OpenAIChatClient()
+
+    messages = [Message(role="user", text="test")]
+    options = {"conversation_id": "12345", "temperature": 0.7}
+
+    prepared_options = client._prepare_options(messages, options)
+
+    # conversation_id is not a valid parameter for AsyncCompletions.create()
+    assert "conversation_id" not in prepared_options
+    # Other options should still be present
+    assert prepared_options["temperature"] == 0.7
+
+
 async def test_streaming_exception_handling(openai_unit_test_env: dict[str, str]) -> None:
     """Test that streaming errors are properly handled."""
     client = OpenAIChatClient()

python/packages/core/tests/workflow/test_function_executor.py

@@ -544,19 +544,19 @@ class TestFunctionExecutor:
         static_wrapped = staticmethod(my_async_func)
 
         # Direct check on descriptor object fails (this is the bug)
-        assert not asyncio.iscoroutinefunction(static_wrapped)
+        assert not asyncio.iscoroutinefunction(static_wrapped)  # type: ignore[reportDeprecated]
         assert isinstance(static_wrapped, staticmethod)
 
         # But unwrapping __func__ reveals the async function
         unwrapped = static_wrapped.__func__
-        assert asyncio.iscoroutinefunction(unwrapped)
+        assert asyncio.iscoroutinefunction(unwrapped)  # type: ignore[reportDeprecated]
 
         # When accessed via class attribute, Python's descriptor protocol
         # automatically unwraps it, so it works:
         class C:
             async_static = static_wrapped
 
-        assert asyncio.iscoroutinefunction(C.async_static)  # Works via descriptor protocol
+        assert asyncio.iscoroutinefunction(C.async_static)  # type: ignore[reportDeprecated]  # Works via descriptor protocol
 
 
 class TestExecutorExplicitTypes:

python/packages/declarative/agent_framework_declarative/_workflows/_executors_tools.py

@@ -15,11 +15,10 @@ import json
 import logging
 import uuid
 from abc import abstractmethod
-from collections.abc import Mapping
+from collections.abc import Callable, Mapping
 from dataclasses import dataclass, field
 from inspect import isawaitable
 from typing import Any, cast
-from collections.abc import Callable
 
 from agent_framework import (
     Content,

python/packages/devui/agent_framework_devui/models/_discovery_models.py

@@ -5,8 +5,8 @@
 from __future__ import annotations
 
 import re
-from typing import Any, cast
 from collections.abc import Callable
+from typing import Any, cast
 
 from pydantic import BaseModel, Field, field_validator
 

python/packages/github_copilot/agent_framework_github_copilot/_agent.py

@@ -26,12 +26,11 @@ from agent_framework._tools import FunctionTool, ToolTypes
 from agent_framework._types import AgentRunInputs, normalize_tools
 from agent_framework.exceptions import AgentException
 from copilot import CopilotClient, CopilotSession
-from copilot.generated.session_events import SessionEvent, SessionEventType
+from copilot.generated.session_events import PermissionRequest, SessionEvent, SessionEventType
 from copilot.types import (
     CopilotClientOptions,
     MCPServerConfig,
     MessageOptions,
-    PermissionRequest,
     PermissionRequestResult,
     ResumeSessionConfig,
     SessionConfig,
@@ -529,7 +528,7 @@ class GitHubCopilotAgent(BaseAgent, Generic[OptionsT]):
         """Convert an FunctionTool to a Copilot SDK tool."""
 
         async def handler(invocation: ToolInvocation) -> ToolResult:
-            args = invocation.get("arguments", {})
+            args: dict[str, Any] = invocation.arguments or {}
             try:
                 if ai_func.input_model:
                     args_instance = ai_func.input_model(**args)
@@ -537,13 +536,13 @@ class GitHubCopilotAgent(BaseAgent, Generic[OptionsT]):
                 else:
                     result = await ai_func.invoke(arguments=args)
                 return ToolResult(
-                    textResultForLlm=str(result),
+                    text_result_for_llm=str(result),
-                    resultType="success",
+                    result_type="success",
                 )
             except Exception as e:
                 return ToolResult(
-                    textResultForLlm=f"Error: {e}",
+                    text_result_for_llm=f"Error: {e}",
-                    resultType="failure",
+                    result_type="failure",
                     error=str(e),
                 )
 

python/packages/github_copilot/pyproject.toml

@@ -3,7 +3,7 @@ name = "agent-framework-github-copilot"
 description = "GitHub Copilot integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
-requires-python = ">=3.10"
+requires-python = ">=3.11"
 version = "1.0.0b260304"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
@@ -15,7 +15,6 @@ classifiers = [
   "Development Status :: 4 - Beta",
   "Intended Audience :: Developers",
   "Programming Language :: Python :: 3",
-  "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",
   "Programming Language :: Python :: 3.13",
@@ -24,7 +23,7 @@ classifiers = [
 ]
 dependencies = [
     "agent-framework-core>=1.0.0rc3",
-    "github-copilot-sdk>=0.1.0",
+    "github-copilot-sdk>=0.1.32",
 ]
 
 [tool.uv]
@@ -66,7 +65,7 @@ include = ["agent_framework_github_copilot"]
 [tool.mypy]
 plugins = ['pydantic.mypy']
 strict = true
-python_version = "3.10"
+python_version = "3.11"
 ignore_missing_imports = true
 disallow_untyped_defs = true
 no_implicit_optional = true

python/packages/github_copilot/tests/test_github_copilot_agent.py

@@ -16,6 +16,7 @@ from agent_framework import (
 )
 from agent_framework.exceptions import AgentException
 from copilot.generated.session_events import Data, SessionEvent, SessionEventType
+from copilot.types import ToolInvocation, ToolResult
 
 from agent_framework_github_copilot import GitHubCopilotAgent, GitHubCopilotOptions
 
@@ -745,10 +746,11 @@ class TestGitHubCopilotAgentToolConversion:
         config = call_args[0][0]
         copilot_tool = config["tools"][0]
 
-        result = await copilot_tool.handler({"arguments": {"arg": "test"}})
+        result = await copilot_tool.handler(ToolInvocation(arguments={"arg": "test"}))
 
-        assert result["resultType"] == "success"
+        assert isinstance(result, ToolResult)
-        assert result["textResultForLlm"] == "Result: test"
+        assert result.result_type == "success"
+        assert result.text_result_for_llm == "Result: test"
 
     async def test_tool_handler_returns_failure_result_on_error(
         self,
@@ -770,11 +772,61 @@ class TestGitHubCopilotAgentToolConversion:
         config = call_args[0][0]
         copilot_tool = config["tools"][0]
 
-        result = await copilot_tool.handler({"arguments": {"arg": "test"}})
+        result = await copilot_tool.handler(ToolInvocation(arguments={"arg": "test"}))
 
-        assert result["resultType"] == "failure"
+        assert isinstance(result, ToolResult)
-        assert "Something went wrong" in result["textResultForLlm"]
+        assert result.result_type == "failure"
-        assert "Something went wrong" in result["error"]
+        assert "Something went wrong" in result.text_result_for_llm
+        assert "Something went wrong" in result.error
+
+    async def test_tool_handler_rejects_raw_dict_invocation(
+        self,
+        mock_client: MagicMock,
+        mock_session: MagicMock,
+    ) -> None:
+        """Test that tool handler raises TypeError when called with a raw dict instead of ToolInvocation."""
+
+        def my_tool(arg: str) -> str:
+            """A test tool."""
+            return f"Result: {arg}"
+
+        agent = GitHubCopilotAgent(client=mock_client, tools=[my_tool])
+        await agent.start()
+
+        await agent._get_or_create_session(AgentSession())  # type: ignore
+
+        call_args = mock_client.create_session.call_args
+        config = call_args[0][0]
+        copilot_tool = config["tools"][0]
+
+        with pytest.raises((TypeError, AttributeError)):
+            await copilot_tool.handler({"arguments": {"arg": "test"}})
+
+    async def test_tool_handler_with_empty_arguments(
+        self,
+        mock_client: MagicMock,
+        mock_session: MagicMock,
+    ) -> None:
+        """Test that tool handler handles ToolInvocation with empty arguments."""
+
+        def no_args_tool() -> str:
+            """A tool with no arguments."""
+            return "no args result"
+
+        agent = GitHubCopilotAgent(client=mock_client, tools=[no_args_tool])
+        await agent.start()
+
+        await agent._get_or_create_session(AgentSession())  # type: ignore
+
+        call_args = mock_client.create_session.call_args
+        config = call_args[0][0]
+        copilot_tool = config["tools"][0]
+
+        result = await copilot_tool.handler(ToolInvocation(arguments={}))
+
+        assert isinstance(result, ToolResult)
+        assert result.result_type == "success"
+        assert result.text_result_for_llm == "no args result"
 
     def test_copilot_tool_passthrough(
         self,
@@ -784,7 +836,7 @@ class TestGitHubCopilotAgentToolConversion:
         from copilot.types import Tool as CopilotTool
 
         async def tool_handler(invocation: Any) -> Any:
-            return {"textResultForLlm": "result", "resultType": "success"}
+            return {"text_result_for_llm": "result", "result_type": "success"}
 
         copilot_tool = CopilotTool(
             name="direct_tool",
@@ -813,7 +865,7 @@ class TestGitHubCopilotAgentToolConversion:
             return arg
 
         async def tool_handler(invocation: Any) -> Any:
-            return {"textResultForLlm": "result", "resultType": "success"}
+            return {"text_result_for_llm": "result", "result_type": "success"}
 
         copilot_tool = CopilotTool(
             name="direct_tool",

python/samples/02-agents/providers/azure_ai/README.md

@@ -1,6 +1,6 @@
 # Azure AI Agent Examples
 
-This folder contains examples demonstrating different ways to create and use agents with the Azure AI client from the `agent_framework.azure` package. These examples use the `AzureAIClient` with the `azure-ai-projects` 2.x (V2) API surface (see [changelog](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-projects/CHANGELOG.md#200b1-2025-11-11)). For V1 (`azure-ai-agents` 1.x) samples using `AzureAIAgentClient`, see the [Azure AI V1 examples folder](../azure_ai_agent/).
+This folder contains examples demonstrating different ways to create and use agents with the Azure AI client from the `agent_framework.azure` package. These examples use the `AzureAIClient` with the `azure-ai-projects` 2.x (V2) API surface (see [changelog](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-projects/CHANGELOG.md#200b1-2025-11-11)). For V1 (`azure-ai-agents` 1.x) samples using `AzureAIAgentClient`, see the [Azure AI V1 examples folder](../azure_ai_agent/). When using preview-only agent creation features on GA SDK versions, create `AIProjectClient` with `allow_preview=True`.
 
 ## Examples
 

python/samples/02-agents/providers/github_copilot/github_copilot_with_file_operations.py

@@ -15,16 +15,18 @@ SECURITY NOTE: Only enable file permissions when you trust the agent's actions.
 import asyncio
 
 from agent_framework.github import GitHubCopilotAgent
-from copilot.types import PermissionRequest, PermissionRequestResult
+from copilot.generated.session_events import PermissionRequest
+from copilot.types import PermissionRequestResult
 
 
-def prompt_permission(request: PermissionRequest, context: dict[str, str]) -> PermissionRequestResult:
+def prompt_permission(
+    request: PermissionRequest, context: dict[str, str]
+) -> PermissionRequestResult:
     """Permission handler that prompts the user for approval."""
-    kind = request.get("kind", "unknown")
+    print(f"\n[Permission Request: {request.kind}]")
-    print(f"\n[Permission Request: {kind}]")
 
-    if "path" in request:
+    if request.path is not None:
-        print(f"  Path: {request.get('path')}")
+        print(f"  Path: {request.path}")
 
     response = input("Approve? (y/n): ").strip().lower()
     if response in ("y", "yes"):

python/samples/02-agents/providers/github_copilot/github_copilot_with_mcp.py

@@ -15,7 +15,8 @@ of MCP-related actions.
 import asyncio
 
 from agent_framework.github import GitHubCopilotAgent
-from copilot.types import MCPServerConfig, PermissionRequest, PermissionRequestResult
+from copilot.generated.session_events import PermissionRequest
+from copilot.types import MCPServerConfig, PermissionRequestResult
 from dotenv import load_dotenv
 
 # Load environment variables from .env file
@@ -24,8 +25,7 @@ load_dotenv()
 
 def prompt_permission(request: PermissionRequest, context: dict[str, str]) -> PermissionRequestResult:
     """Permission handler that prompts the user for approval."""
-    kind = request.get("kind", "unknown")
+    print(f"\n[Permission Request: {request.kind}]")
-    print(f"\n[Permission Request: {kind}]")
 
     response = input("Approve? (y/n): ").strip().lower()
     if response in ("y", "yes"):

python/samples/02-agents/providers/github_copilot/github_copilot_with_multiple_permissions.py

@@ -21,18 +21,18 @@ More permissions mean more potential for unintended actions.
 import asyncio
 
 from agent_framework.github import GitHubCopilotAgent
-from copilot.types import PermissionRequest, PermissionRequestResult
+from copilot.generated.session_events import PermissionRequest
+from copilot.types import PermissionRequestResult
 
 
 def prompt_permission(request: PermissionRequest, context: dict[str, str]) -> PermissionRequestResult:
     """Permission handler that prompts the user for approval."""
-    kind = request.get("kind", "unknown")
+    print(f"\n[Permission Request: {request.kind}]")
-    print(f"\n[Permission Request: {kind}]")
 
-    if "command" in request:
+    if request.full_command_text is not None:
-        print(f"  Command: {request.get('command')}")
+        print(f"  Command: {request.full_command_text}")
-    if "path" in request:
+    if request.path is not None:
-        print(f"  Path: {request.get('path')}")
+        print(f"  Path: {request.path}")
 
     response = input("Approve? (y/n): ").strip().lower()
     if response in ("y", "yes"):

python/samples/02-agents/providers/github_copilot/github_copilot_with_shell.py

@@ -14,16 +14,16 @@ Shell commands have full access to your system within the permissions of the run
 import asyncio
 
 from agent_framework.github import GitHubCopilotAgent
-from copilot.types import PermissionRequest, PermissionRequestResult
+from copilot.generated.session_events import PermissionRequest
+from copilot.types import PermissionRequestResult
 
 
 def prompt_permission(request: PermissionRequest, context: dict[str, str]) -> PermissionRequestResult:
     """Permission handler that prompts the user for approval."""
-    kind = request.get("kind", "unknown")
+    print(f"\n[Permission Request: {request.kind}]")
-    print(f"\n[Permission Request: {kind}]")
 
-    if "command" in request:
+    if request.full_command_text is not None:
-        print(f"  Command: {request.get('command')}")
+        print(f"  Command: {request.full_command_text}")
 
     response = input("Approve? (y/n): ").strip().lower()
     if response in ("y", "yes"):

python/samples/02-agents/providers/github_copilot/github_copilot_with_url.py

@@ -14,16 +14,16 @@ URL fetching allows the agent to access any URL accessible from your network.
 import asyncio
 
 from agent_framework.github import GitHubCopilotAgent
-from copilot.types import PermissionRequest, PermissionRequestResult
+from copilot.generated.session_events import PermissionRequest
+from copilot.types import PermissionRequestResult
 
 
 def prompt_permission(request: PermissionRequest, context: dict[str, str]) -> PermissionRequestResult:
     """Permission handler that prompts the user for approval."""
-    kind = request.get("kind", "unknown")
+    print(f"\n[Permission Request: {request.kind}]")
-    print(f"\n[Permission Request: {kind}]")
 
-    if "url" in request:
+    if request.url is not None:
-        print(f"  URL: {request.get('url')}")
+        print(f"  URL: {request.url}")
 
     response = input("Approve? (y/n): ").strip().lower()
     if response in ("y", "yes"):