Add DI wiring verification tests for AddA2AServer

Add three tests to A2AServerServiceCollectionExtensionsTests that verify custom keyed services are actually wired through to the A2AServer, not just that the server resolves non-null: - Custom IAgentHandler: verifies the keyed handler is invoked when processing a SendMessageRequest instead of the default A2AAgentHandler. - Custom AgentSessionStore (no handler): verifies the keyed session store's GetSessionAsync is called during request processing when no custom handler is registered. - Default stores end-to-end: verifies the InMemoryAgentSessionStore and InMemoryTaskStore defaults successfully process a request. Uses a new CreateAgentMockForRequests helper that includes SerializeSessionCoreAsync setup needed by InMemoryAgentSessionStore. All tests call A2AServer.SendMessageAsync directly (no HTTP layer needed) and use CancellationToken timeouts to guard against hangs. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
fix formatting issues
2026-06-16 21:04:09 +08:00 · 2026-04-22 16:25:16 +01:00 · 2026-04-22 13:44:22 +01:00 · 2026-04-22 13:31:14 +01:00 · 2026-04-22 12:51:51 +01:00 · 2026-04-22 11:44:54 +01:00
52 changed files with 197 additions and 1697 deletions
@@ -108,10 +108,6 @@ jobs:
    needs: team_check
    if: ${{ needs.team_check.outputs.is_team_member == 'true' }}
    timeout-minutes: 60
-    # Advisory check: failures here should not block the PR. The reviewer
-    # posts comments as a best-effort signal; if the pipeline breaks, the
-    # PR author should still be able to merge without a red required check.
-    continue-on-error: true

    steps:
      # Safe checkout: base repo only, not the untrusted PR head.
@@ -87,14 +87,6 @@ jobs:
          -n logical --dist worksteal
          --timeout=120 --session-timeout=900 --timeout_method thread
          --retries 2 --retry-delay 5
-          --junitxml=pytest.xml
-      - name: Upload test results
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: test-results-openai
-          path: ./python/pytest.xml
-          if-no-files-found: ignore

  # Azure OpenAI integration tests
  python-tests-azure-openai:
@@ -138,14 +130,6 @@ jobs:
          -n logical --dist worksteal
          --timeout=120 --session-timeout=900 --timeout_method thread
          --retries 2 --retry-delay 5
-          --junitxml=pytest.xml
-      - name: Upload test results
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: test-results-azure-openai
-          path: ./python/pytest.xml
-          if-no-files-found: ignore

  # Misc integration tests (Anthropic, Hyperlight, Ollama, MCP)
  python-tests-misc-integration:
@@ -189,14 +173,6 @@ jobs:
          -n logical --dist worksteal
          --timeout=120 --session-timeout=900 --timeout_method thread
          --retries 2 --retry-delay 30
-          --junitxml=pytest.xml
-      - name: Upload test results
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: test-results-misc
-          path: ./python/pytest.xml
-          if-no-files-found: ignore
      - name: Stop local MCP server
        if: always()
        shell: bash
@@ -273,14 +249,6 @@ jobs:
          -x
          --timeout=360 --session-timeout=900 --timeout_method thread
          --retries 2 --retry-delay 5
-          --junitxml=pytest.xml
-      - name: Upload test results
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: test-results-functions
-          path: ./python/pytest.xml
-          if-no-files-found: ignore

  # Foundry integration tests
  python-tests-foundry:
@@ -327,14 +295,6 @@ jobs:
          -n logical --dist worksteal
          --timeout=120 --session-timeout=900 --timeout_method thread
          --retries 2 --retry-delay 5
-          --junitxml=pytest.xml
-      - name: Upload test results
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: test-results-foundry
-          path: ./python/pytest.xml
-          if-no-files-found: ignore

  # Azure Cosmos integration tests
  python-tests-cosmos:
@@ -379,80 +339,7 @@ jobs:
          echo "Cosmos DB emulator did not become ready in time." >&2
          exit 1
      - name: Test with pytest (Cosmos integration)
-        run: uv run --directory packages/azure-cosmos poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5 --junitxml=${{ github.workspace }}/python/pytest.xml
-      - name: Upload test results
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: test-results-cosmos
-          path: ./python/pytest.xml
-          if-no-files-found: ignore
-
-  # Flaky test trend report (aggregates per-job JUnit XML results)
-  python-flaky-test-report:
-    name: Flaky Test Report
-    if: >
-      always() &&
-      (contains(join(needs.*.result, ','), 'success') ||
-       contains(join(needs.*.result, ','), 'failure'))
-    needs:
-      [
-        python-tests-openai,
-        python-tests-azure-openai,
-        python-tests-misc-integration,
-        python-tests-functions,
-        python-tests-foundry,
-        python-tests-cosmos,
-      ]
-    runs-on: ubuntu-latest
-    defaults:
-      run:
-        working-directory: python
-    steps:
-      - uses: actions/checkout@v6
-        with:
-          ref: ${{ inputs.checkout-ref }}
-          persist-credentials: false
-      - name: Set up python and install the project
-        uses: ./.github/actions/python-setup
-        with:
-          python-version: ${{ env.UV_PYTHON }}
-          os: ${{ runner.os }}
-      - name: Download all test results from current run
-        uses: actions/download-artifact@v4
-        with:
-          pattern: test-results-*
-          path: test-results/
-      - name: Restore flaky report history cache
-        uses: actions/cache/restore@v4
-        with:
-          path: python/flaky-report-history.json
-          key: flaky-report-history-integration-${{ github.run_id }}
-          restore-keys: |
-            flaky-report-history-integration-
-      - name: Generate trend report
-        run: >
-          uv run python scripts/flaky_report/aggregate.py
-          ../test-results/
-          flaky-report-history.json
-          flaky-test-report.md
-      - name: Post to Job Summary
-        if: always()
-        run: cat flaky-test-report.md >> $GITHUB_STEP_SUMMARY
-      - name: Save flaky report history cache
-        if: always()
-        uses: actions/cache/save@v4
-        with:
-          path: python/flaky-report-history.json
-          key: flaky-report-history-integration-${{ github.run_id }}
-      - name: Upload unified trend report
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: flaky-test-report
-          path: |
-            python/flaky-test-report.md
-            python/flaky-report-history.json
+        run: uv run --directory packages/azure-cosmos poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5

  python-integration-tests-check:
    if: always()
@@ -181,13 +181,6 @@ jobs:
          display-options: fEX
          fail-on-empty: false
          title: OpenAI integration test results
-      - name: Upload test results
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: test-results-openai
-          path: ./python/pytest.xml
-          if-no-files-found: ignore

  # Azure OpenAI integration tests
  python-tests-azure-openai:
@@ -251,13 +244,6 @@ jobs:
          display-options: fEX
          fail-on-empty: false
          title: Azure OpenAI integration test results
-      - name: Upload test results
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: test-results-azure-openai
-          path: ./python/pytest.xml
-          if-no-files-found: ignore

  # Misc integration tests (Anthropic, Ollama, MCP)
  python-tests-misc-integration:
@@ -335,13 +321,6 @@ jobs:
          display-options: fEX
          fail-on-empty: false
          title: Misc integration test results
-      - name: Upload test results
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: test-results-misc
-          path: ./python/pytest.xml
-          if-no-files-found: ignore

  # Azure Functions + Durable Task integration tests
  python-tests-functions:
@@ -413,13 +392,6 @@ jobs:
          display-options: fEX
          fail-on-empty: false
          title: Functions integration test results
-      - name: Upload test results
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: test-results-functions
-          path: ./python/pytest.xml
-          if-no-files-found: ignore

  python-tests-foundry:
    name: Python Integration Tests - Foundry
@@ -437,10 +409,6 @@ jobs:
      FOUNDRY_MODEL: ${{ vars.FOUNDRY_MODEL }}
      FOUNDRY_AGENT_NAME: ${{ vars.FOUNDRY_AGENT_NAME }}
      FOUNDRY_AGENT_VERSION: ${{ vars.FOUNDRY_AGENT_VERSION }}
-      FOUNDRY_MODELS_ENDPOINT: ${{ vars.FOUNDRY_MODELS_ENDPOINT || '' }}
-      FOUNDRY_MODELS_API_KEY: ${{ secrets.FOUNDRY_MODELS_API_KEY || '' }}
-      FOUNDRY_EMBEDDING_MODEL: ${{ vars.FOUNDRY_EMBEDDING_MODEL || '' }}
-      FOUNDRY_IMAGE_EMBEDDING_MODEL: ${{ vars.FOUNDRY_IMAGE_EMBEDDING_MODEL || '' }}
      LOCAL_MCP_URL: ${{ vars.LOCAL_MCP__URL }}
    defaults:
      run:
@@ -480,13 +448,6 @@ jobs:
          display-options: fEX
          fail-on-empty: false
          title: Test results
-      - name: Upload test results
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: test-results-foundry
-          path: ./python/pytest.xml
-          if-no-files-found: ignore

  # TODO: Add python-tests-lab

@@ -536,7 +497,7 @@ jobs:
          echo "Cosmos DB emulator did not become ready in time." >&2
          exit 1
      - name: Test with pytest (Cosmos integration)
-        run: uv run --directory packages/azure-cosmos poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5 --junitxml=${{ github.workspace }}/python/pytest.xml
+        run: uv run --directory packages/azure-cosmos poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5 --junitxml=pytest.xml
        working-directory: ./python
      - name: Surface failing tests
        if: always()
@@ -547,76 +508,6 @@ jobs:
          display-options: fEX
          fail-on-empty: false
          title: Cosmos integration test results
-      - name: Upload test results
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: test-results-cosmos
-          path: ./python/pytest.xml
-          if-no-files-found: ignore
-
-  # Flaky test trend report (aggregates per-job JUnit XML results)
-  python-flaky-test-report:
-    name: Flaky Test Report
-    if: >
-      always() &&
-      (contains(join(needs.*.result, ','), 'success') ||
-       contains(join(needs.*.result, ','), 'failure'))
-    needs:
-      [
-        python-tests-openai,
-        python-tests-azure-openai,
-        python-tests-misc-integration,
-        python-tests-functions,
-        python-tests-foundry,
-        python-tests-cosmos,
-      ]
-    runs-on: ubuntu-latest
-    defaults:
-      run:
-        working-directory: python
-    steps:
-      - uses: actions/checkout@v6
-      - name: Set up python and install the project
-        uses: ./.github/actions/python-setup
-        with:
-          python-version: ${{ env.UV_PYTHON }}
-          os: ${{ runner.os }}
-      - name: Download all test results from current run
-        uses: actions/download-artifact@v4
-        with:
-          pattern: test-results-*
-          path: test-results/
-      - name: Restore flaky report history cache
-        uses: actions/cache/restore@v4
-        with:
-          path: python/flaky-report-history.json
-          key: flaky-report-history-merge-${{ github.run_id }}
-          restore-keys: |
-            flaky-report-history-merge-
-      - name: Generate trend report
-        run: >
-          uv run python scripts/flaky_report/aggregate.py
-          ../test-results/
-          flaky-report-history.json
-          flaky-test-report.md
-      - name: Post to Job Summary
-        if: always()
-        run: cat flaky-test-report.md >> $GITHUB_STEP_SUMMARY
-      - name: Save flaky report history cache
-        if: always()
-        uses: actions/cache/save@v4
-        with:
-          path: python/flaky-report-history.json
-          key: flaky-report-history-merge-${{ github.run_id }}
-      - name: Upload unified trend report
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: flaky-test-report
-          path: |
-            python/flaky-test-report.md
-            python/flaky-report-history.json

  python-integration-tests-check:
    if: always()
@@ -7,24 +7,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

 ## [Unreleased]

-## [1.1.1] - 2026-04-23
-
-### Added
- **agent-framework-core**: Add `expected_output` ground-truth support to `evaluate_workflow` for similarity evaluators ([#5234](https://github.com/microsoft/agent-framework/pull/5234))
- **agent-framework-ag-ui**, **agent-framework-a2a**: Propagate `thread_id` and `forwarded_props` through AG-UI to A2A `context_id` ([#5383](https://github.com/microsoft/agent-framework/pull/5383))
- **samples**: Add second approval-required tool (`set_stop_loss`) to `concurrent_builder_tool_approval` sample ([#4875](https://github.com/microsoft/agent-framework/pull/4875))
-
-### Changed
- **agent-framework-foundry-hosting**: Correct Development Status classifier from Beta (4) to Alpha (3) to match the package's lifecycle stage ([#5387](https://github.com/microsoft/agent-framework/pull/5387))
- **tests**: Add Python flaky test report workflow ([#5342](https://github.com/microsoft/agent-framework/pull/5342))
-
-### Fixed
- **agent-framework-openai**: Fix OpenAI Responses streaming to propagate `created_at` from the final `response.completed` event ([#5382](https://github.com/microsoft/agent-framework/pull/5382))
- **agent-framework-openai**: Fix `OpenAIEmbeddingClient` to use `AsyncOpenAI` for `/openai/v1` endpoints ([#5137](https://github.com/microsoft/agent-framework/pull/5137))
- **agent-framework-openai**: Exclude null `file_id` from `input_image` payload to prevent schema 400 errors ([#5125](https://github.com/microsoft/agent-framework/pull/5125))
- **agent-framework-foundry**: Reconcile Toolbox hosted-tool payloads with the Responses API ([#5414](https://github.com/microsoft/agent-framework/pull/5414))
- **agent-framework-ag-ui**: Pass client `thread_id` as `session_id` when constructing `AgentSession` ([#5384](https://github.com/microsoft/agent-framework/pull/5384))
-
 ## [1.1.0] - 2026-04-21

 ### Added
@@ -295,10 +295,7 @@ class A2AAgent(AgentTelemetryLayer, BaseAgent):
        else:
            if not normalized_messages:
                raise ValueError("At least one message is required when starting a new task (no continuation_token).")
-            a2a_message = self._prepare_message_for_a2a(
-                normalized_messages[-1],
-                context_id=session.service_session_id if session else None,
-            )
+            a2a_message = self._prepare_message_for_a2a(normalized_messages[-1])
            a2a_stream = self.client.send_message(a2a_message)

        provider_session = session
@@ -587,7 +584,7 @@ class A2AAgent(AgentTelemetryLayer, BaseAgent):
            return AgentResponse.from_updates(updates)
        return AgentResponse(messages=[], response_id=task.id, raw_representation=task)

-    def _prepare_message_for_a2a(self, message: Message, *, context_id: str | None = None) -> A2AMessage:
+    def _prepare_message_for_a2a(self, message: Message) -> A2AMessage:
        """Prepare a Message for the A2A protocol.

        Transforms Agent Framework Message objects into A2A protocol Messages by:
@@ -596,13 +593,6 @@ class A2AAgent(AgentTelemetryLayer, BaseAgent):
        - Converting file references (URI/data/hosted_file) to FilePart objects
        - Preserving metadata and additional properties from the original message
        - Setting the role to 'user' as framework messages are treated as user input
-
-        Args:
-            message: The framework Message to convert.
-            context_id: Optional fallback context identifier (e.g. derived from
-                ``AgentSession.service_session_id``). When the *message* already
-                carries a ``context_id`` in its ``additional_properties`` that
-                value takes precedence; otherwise this fallback is used.
        """
        parts: list[A2APart] = []
        if not message.contents:
@@ -682,7 +672,7 @@ class A2AAgent(AgentTelemetryLayer, BaseAgent):
            role=A2ARole("user"),
            parts=parts,
            message_id=message.message_id or uuid.uuid4().hex,
-            context_id=message.additional_properties.get("context_id") or context_id,
+            context_id=message.additional_properties.get("context_id"),
            metadata=metadata,
        )

@@ -4,7 +4,7 @@ description = "A2A integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
    "a2a-sdk>=0.3.5,<0.3.24",
 ]

@@ -46,7 +46,6 @@ class MockA2AClient:
        self.responses: list[Any] = []
        self.resubscribe_responses: list[Any] = []
        self.get_task_response: Task | None = None
-        self.last_message: Any = None

    def add_message_response(self, message_id: str, text: str, role: str = "agent") -> None:
        """Add a mock Message response."""
@@ -112,7 +111,6 @@ class MockA2AClient:

    async def send_message(self, message: Any) -> AsyncIterator[Any]:
        """Mock send_message method that yields responses."""
-        self.last_message = message
        self.call_count += 1

        # All queued responses are delivered as a single streaming batch per call.
@@ -541,37 +539,6 @@ def test_prepare_message_for_a2a_forwards_context_id() -> None:
    assert result.metadata == {"trace_id": "trace-456"}


-def test_prepare_message_for_a2a_uses_fallback_context_id() -> None:
-    """Test that context_id kwarg is used when message has no context_id property."""
-
-    agent = A2AAgent(client=MagicMock(), http_client=None)
-
-    message = Message(
-        role="user",
-        contents=[Content.from_text(text="Hello")],
-    )
-
-    result = agent._prepare_message_for_a2a(message, context_id="session-ctx-1")
-
-    assert result.context_id == "session-ctx-1"
-
-
-def test_prepare_message_for_a2a_message_context_id_takes_precedence() -> None:
-    """Test that message.additional_properties context_id wins over the fallback."""
-
-    agent = A2AAgent(client=MagicMock(), http_client=None)
-
-    message = Message(
-        role="user",
-        contents=[Content.from_text(text="Hello")],
-        additional_properties={"context_id": "explicit-ctx"},
-    )
-
-    result = agent._prepare_message_for_a2a(message, context_id="session-ctx-1")
-
-    assert result.context_id == "explicit-ctx"
-
-
 def test_parse_contents_from_a2a_with_data_part() -> None:
    """Test conversion of A2A DataPart."""

@@ -901,43 +868,6 @@ async def test_poll_task_completed(a2a_agent: A2AAgent, mock_a2a_client: MockA2A
 # endregion


-# region Session context_id Integration Tests
-
-
-@mark.asyncio
-async def test_run_passes_session_service_session_id_as_context_id(mock_a2a_client: MockA2AClient) -> None:
-    """Test that run() wires session.service_session_id to the A2A message context_id."""
-    agent = A2AAgent(name="Test Agent", id="test-agent", client=mock_a2a_client, http_client=None)
-    mock_a2a_client.add_message_response("msg-ctx", "reply")
-
-    session = AgentSession(service_session_id="svc-session-42")
-    await agent.run("Hello", session=session)
-
-    assert mock_a2a_client.last_message is not None
-    assert mock_a2a_client.last_message.context_id == "svc-session-42"
-
-
-@mark.asyncio
-async def test_run_message_context_id_takes_precedence_over_session(mock_a2a_client: MockA2AClient) -> None:
-    """Test that an explicit context_id on the message wins over session.service_session_id."""
-    agent = A2AAgent(name="Test Agent", id="test-agent", client=mock_a2a_client, http_client=None)
-    mock_a2a_client.add_message_response("msg-ctx2", "reply")
-
-    session = AgentSession(service_session_id="svc-session-42")
-    message = Message(
-        role="user",
-        contents=[Content.from_text(text="Hello")],
-        additional_properties={"context_id": "explicit-ctx"},
-    )
-    await agent.run(messages=[message], session=session)
-
-    assert mock_a2a_client.last_message is not None
-    assert mock_a2a_client.last_message.context_id == "explicit-ctx"
-
-
-# endregion
-
-
 # region Context Provider Tests


@@ -790,9 +790,9 @@ async def run_agent_stream(
    # Create session (with service session support)
    if config.use_service_session:
        supplied_thread_id = input_data.get("thread_id") or input_data.get("threadId")
-        session = AgentSession(session_id=thread_id, service_session_id=supplied_thread_id)
+        session = AgentSession(service_session_id=supplied_thread_id)
    else:
-        session = AgentSession(session_id=thread_id)
+        session = AgentSession()

    # Inject metadata for AG-UI orchestration (Feature #2: Azure-safe truncation)
    base_metadata: dict[str, Any] = {
@@ -1,6 +1,6 @@
 [project]
 name = "agent-framework-ag-ui"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 description = "AG-UI protocol integration for Agent Framework"
 readme = "README.md"
 license-files = ["LICENSE"]
@@ -22,7 +22,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
    "ag-ui-protocol==0.1.13",
    "fastapi>=0.115.0,<0.133.1",
    "uvicorn[standard]>=0.30.0,<0.42.0"
@@ -183,7 +183,6 @@ class StubAgent(SupportsAgentRun):
        self.client = client or SimpleNamespace(function_invocation_configuration=None)
        self.messages_received: list[Any] = []
        self.tools_received: list[Any] | None = None
-        self.last_session: AgentSession | None = None

    @overload
    def run(
@@ -217,7 +216,6 @@ class StubAgent(SupportsAgentRun):

            async def _stream() -> AsyncIterator[AgentResponseUpdate]:
                self.messages_received = [] if messages is None else list(messages)  # type: ignore[arg-type]
-                self.last_session = session
                self.tools_received = kwargs.get("tools")
                for update in self.updates:
                    yield update
@@ -1640,115 +1640,3 @@ class TestReasoningInSnapshot:
        # close: MsgEnd(block2) + End(block2)
        assert isinstance(close[0], ReasoningMessageEndEvent)
        assert close[0].message_id == "block2"
-
-
-async def test_session_id_matches_thread_id():
-    """Session created by run_agent_stream uses the client thread_id as session_id."""
-    from conftest import StubAgent
-
-    from agent_framework_ag_ui import AgentFrameworkAgent
-
-    stub = StubAgent()
-    agent = AgentFrameworkAgent(agent=stub)
-
-    payload = {
-        "thread_id": "my-thread-123",
-        "run_id": "run-1",
-        "messages": [{"role": "user", "content": "Hello"}],
-    }
-
-    _ = [event async for event in agent.run(payload)]
-
-    assert stub.last_session is not None
-    assert stub.last_session.session_id == "my-thread-123"
-
-
-async def test_session_id_matches_camel_case_thread_id():
-    """Session uses threadId (camelCase) as session_id when snake_case is absent."""
-    from conftest import StubAgent
-
-    from agent_framework_ag_ui import AgentFrameworkAgent
-
-    stub = StubAgent()
-    agent = AgentFrameworkAgent(agent=stub)
-
-    payload = {
-        "threadId": "camel-thread-456",
-        "run_id": "run-2",
-        "messages": [{"role": "user", "content": "Hello"}],
-    }
-
-    _ = [event async for event in agent.run(payload)]
-
-    assert stub.last_session is not None
-    assert stub.last_session.session_id == "camel-thread-456"
-
-
-async def test_session_id_matches_thread_id_with_service_session():
-    """Session uses thread_id as session_id even when use_service_session is enabled."""
-    from conftest import StubAgent
-
-    from agent_framework_ag_ui import AgentFrameworkAgent
-
-    stub = StubAgent()
-    agent = AgentFrameworkAgent(agent=stub, use_service_session=True)
-
-    payload = {
-        "thread_id": "service-thread-789",
-        "run_id": "run-3",
-        "messages": [{"role": "user", "content": "Hello"}],
-    }
-
-    _ = [event async for event in agent.run(payload)]
-
-    assert stub.last_session is not None
-    assert stub.last_session.session_id == "service-thread-789"
-    assert stub.last_session.service_session_id == "service-thread-789"
-
-
-async def test_session_id_generated_when_no_thread_id():
-    """Session gets a generated UUID as session_id when no thread_id is provided."""
-    import uuid
-
-    from conftest import StubAgent
-
-    from agent_framework_ag_ui import AgentFrameworkAgent
-
-    stub = StubAgent()
-    agent = AgentFrameworkAgent(agent=stub)
-
-    payload = {
-        "run_id": "run-4",
-        "messages": [{"role": "user", "content": "Hello"}],
-    }
-
-    _ = [event async for event in agent.run(payload)]
-
-    assert stub.last_session is not None
-    # Should be a valid UUID (auto-generated)
-    uuid.UUID(stub.last_session.session_id)
-
-
-async def test_service_session_no_thread_id_generates_uuid():
-    """With use_service_session=True and no thread_id, session_id is a UUID and service_session_id is None."""
-    import uuid
-
-    from conftest import StubAgent
-
-    from agent_framework_ag_ui import AgentFrameworkAgent
-
-    stub = StubAgent()
-    agent = AgentFrameworkAgent(agent=stub, use_service_session=True)
-
-    payload = {
-        "run_id": "run-5",
-        "messages": [{"role": "user", "content": "Hello"}],
-    }
-
-    _ = [event async for event in agent.run(payload)]
-
-    assert stub.last_session is not None
-    # session_id should be a valid auto-generated UUID
-    uuid.UUID(stub.last_session.session_id)
-    # service_session_id should be None since no thread_id was supplied
-    assert stub.last_session.service_session_id is None
@@ -4,7 +4,7 @@ description = "Anthropic integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
    "anthropic>=0.80.0,<0.80.1",
 ]

@@ -4,7 +4,7 @@ description = "Azure AI Search integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
    "azure-search-documents>=11.7.0b2,<11.7.0b3",
 ]

@@ -4,7 +4,7 @@ description = "Azure Cosmos DB history provider integration for Microsoft Agent
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
    "azure-cosmos>=4.3.0,<5",
 ]

@@ -4,7 +4,7 @@ description = "Azure Functions integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -22,7 +22,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
    "agent-framework-durabletask",
    "azure-functions>=1.24.0,<2",
    "azure-functions-durable>=1.3.1,<2",
@@ -4,7 +4,7 @@ description = "Amazon Bedrock integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
    "boto3>=1.35.0,<2.0.0",
    "botocore>=1.35.0,<2.0.0",
 ]
@@ -4,7 +4,7 @@ description = "OpenAI ChatKit integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -22,7 +22,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
    "openai-chatkit>=1.4.1,<2.0.0",
 ]

@@ -4,7 +4,7 @@ description = "Claude Agent SDK integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
    "claude-agent-sdk>=0.1.36,<0.1.49",
 ]

@@ -4,7 +4,7 @@ description = "Copilot Studio integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
    "microsoft-agents-copilotstudio-client>=0.3.1,<0.3.2",
 ]

@@ -125,7 +125,6 @@ from ._telemetry import (
    prepend_agent_framework_to_user_agent,
 )
 from ._tools import (
-    SKIP_PARSING,
    FunctionInvocationConfiguration,
    FunctionInvocationLayer,
    FunctionTool,
@@ -259,7 +258,6 @@ __all__ = [
    "GROUP_INDEX_KEY",
    "GROUP_KIND_KEY",
    "GROUP_TOKEN_COUNT_KEY",
-    "SKIP_PARSING",
    "SUMMARIZED_BY_SUMMARY_ID_KEY",
    "SUMMARY_OF_GROUP_IDS_KEY",
    "SUMMARY_OF_MESSAGE_IDS_KEY",
@@ -94,33 +94,6 @@ ApprovalMode: TypeAlias = Literal["always_require", "never_require"]
 ChatClientT = TypeVar("ChatClientT", bound="SupportsChatGetResponse[Any]")
 ResponseModelBoundT = TypeVar("ResponseModelBoundT", bound=BaseModel)

-
-class _SkipParsingSentinel:
-    """Sentinel signaling that :meth:`FunctionTool.invoke` should return the raw value.
-
-    When passed as ``result_parser`` to :class:`FunctionTool` (or the ``@tool`` decorator),
-    the default :meth:`FunctionTool.parse_result` is bypassed and the wrapped function's
-    return value is returned unchanged from :meth:`FunctionTool.invoke`. Callers may also
-    request the raw value on a per-call basis by passing ``skip_parsing=True`` to
-    :meth:`FunctionTool.invoke`.
-
-    Use the module-level ``SKIP_PARSING`` singleton — do not instantiate this class.
-    """
-
-    _instance: ClassVar[_SkipParsingSentinel | None] = None
-
-    def __new__(cls) -> _SkipParsingSentinel:
-        if cls._instance is None:
-            cls._instance = super().__new__(cls)
-        return cls._instance
-
-    def __repr__(self) -> str:
-        return "SKIP_PARSING"
-
-
-SKIP_PARSING: Final[_SkipParsingSentinel] = _SkipParsingSentinel()
-"""Sentinel for ``FunctionTool(result_parser=...)`` meaning "do not parse the result"."""
-
 # region Helpers


@@ -306,7 +279,7 @@ class FunctionTool(SerializationMixin):
        additional_properties: dict[str, Any] | None = None,
        func: Callable[..., Any] | None = None,
        input_model: type[BaseModel] | Mapping[str, Any] | None = None,
-        result_parser: Callable[[Any], str | list[Content]] | _SkipParsingSentinel | None = None,
+        result_parser: Callable[[Any], str | list[Content]] | None = None,
        **kwargs: Any,
    ) -> None:
        """Initialize the FunctionTool.
@@ -354,11 +327,9 @@ class FunctionTool(SerializationMixin):
            result_parser: An optional callable with signature ``Callable[[Any], str]`` that
                overrides the default result parsing behavior. When provided, this callable
                is used to convert the raw function return value to a string instead of the
-                built-in :meth:`parse_result` logic. Pass the :data:`SKIP_PARSING` sentinel
-                instead of a callable to opt out of parsing entirely; in that case
-                :meth:`invoke` returns the wrapped function's raw return value. Depending
-                on your function, it may be easiest to just do the serialization directly
-                in the function body rather than providing a custom ``result_parser``.
+                built-in :meth:`parse_result` logic. Depending on your function, it may be
+                easiest to just do the serialization directly in the function body rather
+                than providing a custom ``result_parser``.
            **kwargs: Additional keyword arguments.
        """
        # Core attributes (formerly from BaseTool)
@@ -537,65 +508,31 @@ class FunctionTool(SerializationMixin):
            self.invocation_exception_count += 1
            raise

-    @overload
    async def invoke(
        self,
        *,
        arguments: BaseModel | Mapping[str, Any] | None = None,
        context: FunctionInvocationContext | None = None,
        tool_call_id: str | None = None,
-        skip_parsing: Literal[True],
        **kwargs: Any,
-    ) -> Any: ...
-
-    @overload
-    async def invoke(
-        self,
-        *,
-        arguments: BaseModel | Mapping[str, Any] | None = None,
-        context: FunctionInvocationContext | None = None,
-        tool_call_id: str | None = None,
-        skip_parsing: Literal[False] = False,
-        **kwargs: Any,
-    ) -> list[Content]: ...
-
-    async def invoke(
-        self,
-        *,
-        arguments: BaseModel | Mapping[str, Any] | None = None,
-        context: FunctionInvocationContext | None = None,
-        tool_call_id: str | None = None,
-        skip_parsing: bool = False,
-        **kwargs: Any,
-    ) -> list[Content] | Any:
+    ) -> list[Content]:
        """Run the AI function with the provided arguments as a Pydantic model.

        The raw return value of the wrapped function is automatically parsed into a
        ``list[Content]`` using :meth:`parse_result` or the custom ``result_parser``
-        configured on the tool. Every result — text, rich media, or serialized
-        objects — is represented uniformly as Content items.
-
-        Parsing can be skipped in two ways: configure the tool with
-        ``result_parser=SKIP_PARSING`` to always skip parsing, or pass
-        ``skip_parsing=True`` per call. Either way the wrapped function's raw value
-        is returned. This is intended for callers (e.g. sandboxed runtimes) that
-        consume the value from Python directly and would otherwise undo the
-        ``Content`` wrapping.
+        if one was provided.  Every result — text, rich media, or serialized objects —
+        is represented uniformly as Content items.

        Keyword Args:
            arguments: A mapping or model instance containing the arguments for the function.
            context: Explicit function invocation context carrying runtime kwargs.
            tool_call_id: Optional tool call identifier used for telemetry and tracing.
-            skip_parsing: When ``True``, bypass parsing and return the wrapped function's
-                raw value instead of a ``list[Content]``. Defaults to ``False``.
            kwargs: Direct function argument values. When provided, every keyword
                must match a declared tool parameter. Runtime data must be passed
                via ``context``.

        Returns:
-            ``list[Content]`` by default. The raw function return value (``Any``) when
-            ``skip_parsing=True`` (or the tool was constructed with
-            ``result_parser=SKIP_PARSING``).
+            A list of Content items representing the tool output.

        Raises:
            TypeError: If arguments is not mapping-like or fails schema checks.
@@ -607,9 +544,7 @@ class FunctionTool(SerializationMixin):
        from ._types import Content
        from .observability import OBSERVABILITY_SETTINGS

-        configured_parser = self.result_parser
-        skip_parsing = skip_parsing or configured_parser is SKIP_PARSING
-        parser = configured_parser if callable(configured_parser) else FunctionTool.parse_result
+        parser = self.result_parser or FunctionTool.parse_result

        parameter_names = set(self.parameters().get("properties", {}).keys())
        direct_argument_kwargs = (
@@ -681,10 +616,6 @@ class FunctionTool(SerializationMixin):
            logger.debug(f"Function arguments: {observable_kwargs}")
            res = self.__call__(**call_kwargs)
            result = await res if inspect.isawaitable(res) else res
-            if skip_parsing:
-                logger.info(f"Function {self.name} succeeded.")
-                logger.debug(f"Function result: {type(result).__name__}")
-                return result
            try:
                parsed = parser(result)
            except Exception:
@@ -740,13 +671,6 @@ class FunctionTool(SerializationMixin):
                logger.error(f"Function failed. Error: {exception}")
                raise
            else:
-                if skip_parsing:
-                    logger.info(f"Function {self.name} succeeded.")
-                    if OBSERVABILITY_SETTINGS.SENSITIVE_DATA_ENABLED:  # type: ignore[name-defined]
-                        result_str = str(result)
-                        span.set_attribute(OtelAttr.TOOL_RESULT, result_str)
-                        logger.debug(f"Function result: {result_str}")
-                    return result
                try:
                    parsed = parser(result)
                except Exception:
@@ -1143,7 +1067,7 @@ def tool(
    max_invocations: int | None = None,
    max_invocation_exceptions: int | None = None,
    additional_properties: dict[str, Any] | None = None,
-    result_parser: Callable[[Any], str | list[Content]] | _SkipParsingSentinel | None = None,
+    result_parser: Callable[[Any], str | list[Content]] | None = None,
 ) -> FunctionTool: ...


@@ -1159,7 +1083,7 @@ def tool(
    max_invocations: int | None = None,
    max_invocation_exceptions: int | None = None,
    additional_properties: dict[str, Any] | None = None,
-    result_parser: Callable[[Any], str | list[Content]] | _SkipParsingSentinel | None = None,
+    result_parser: Callable[[Any], str | list[Content]] | None = None,
 ) -> Callable[[Callable[..., Any]], FunctionTool]: ...


@@ -1174,7 +1098,7 @@ def tool(
    max_invocations: int | None = None,
    max_invocation_exceptions: int | None = None,
    additional_properties: dict[str, Any] | None = None,
-    result_parser: Callable[[Any], str | list[Content]] | _SkipParsingSentinel | None = None,
+    result_parser: Callable[[Any], str | list[Content]] | None = None,
 ) -> FunctionTool | Callable[[Callable[..., Any]], FunctionTool]:
    """Decorate a function to turn it into a FunctionTool that can be passed to models and executed automatically.

@@ -4,7 +4,7 @@ description = "Microsoft Agent Framework for building AI Agents with Python. Thi
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.1.1"
+version = "1.1.0"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -8,7 +8,6 @@ from opentelemetry.sdk.trace.export.in_memory_span_exporter import InMemorySpanE
 from pydantic import BaseModel

 from agent_framework import (
-    SKIP_PARSING,
    Content,
    FunctionTool,
    tool,
@@ -1301,165 +1300,4 @@ def test_normalize_tools_flattens_mapping_like_toolbox_with_tools_attr() -> None
    assert normalized[1] is standalone


-# region SKIP_PARSING sentinel & skip_parsing
-
-
-async def test_invoke_skip_parsing_returns_native_value() -> None:
-    """invoke(skip_parsing=True) returns the wrapped function's raw value."""
-
-    @tool
-    def get_weather(city: str) -> dict[str, Any]:
-        """Get the weather."""
-        return {"city": city, "temperature_c": 21.5, "conditions": "partly cloudy"}
-
-    raw = await get_weather.invoke(arguments={"city": "Seattle"}, skip_parsing=True)
-
-    assert isinstance(raw, dict)
-    assert raw == {"city": "Seattle", "temperature_c": 21.5, "conditions": "partly cloudy"}
-
-
-async def test_invoke_skip_parsing_passes_through_custom_objects() -> None:
-    """skip_parsing must not call str()/repr() on the result."""
-
-    class Custom:  # noqa: B903
-        def __init__(self, value: int) -> None:
-            self.value = value
-
-    @tool
-    def make() -> Custom:
-        """Make a custom object."""
-        return Custom(42)
-
-    raw = await make.invoke(skip_parsing=True)
-
-    assert isinstance(raw, Custom)
-    assert raw.value == 42
-
-
-async def test_invoke_skip_parsing_awaits_async_functions() -> None:
-    @tool
-    async def slow(x: int) -> int:
-        """Async tool."""
-        return x * 2
-
-    raw = await slow.invoke(arguments={"x": 21}, skip_parsing=True)
-    assert raw == 42
-
-
-async def test_invoke_skip_parsing_bypasses_configured_result_parser() -> None:
-    """The tool's own result_parser is bypassed when skip_parsing=True is requested."""
-    parser_calls: list[Any] = []
-
-    def parser(value: Any) -> str:
-        parser_calls.append(value)
-        return "PARSED"
-
-    @tool(result_parser=parser)
-    def make_dict() -> dict[str, int]:
-        """Returns a dict."""
-        return {"a": 1}
-
-    raw = await make_dict.invoke(skip_parsing=True)
-    assert raw == {"a": 1}
-    assert parser_calls == []
-
-    # Sanity: omitting skip_parsing still applies the configured parser.
-    parsed = await make_dict.invoke()
-    assert parsed[0].type == "text"
-    assert parsed[0].text == "PARSED"
-
-
-async def test_constructor_skip_parsing_sentinel_returns_raw_by_default() -> None:
-    """Constructing a tool with result_parser=SKIP_PARSING makes invoke return the raw value."""
-
-    @tool(result_parser=SKIP_PARSING)
-    def make_dict() -> dict[str, int]:
-        """Returns a dict."""
-        return {"a": 1}
-
-    raw = await make_dict.invoke()
-    assert raw == {"a": 1}
-
-
-async def test_invoke_skip_parsing_validates_arguments() -> None:
-    """Argument validation is shared with the default path."""
-
-    @tool
-    def adder(x: int, y: int) -> int:
-        """Add."""
-        return x + y
-
-    with pytest.raises(TypeError):
-        await adder.invoke(arguments={"x": "not-an-int", "y": 1}, skip_parsing=True)
-
-
-async def test_invoke_skip_parsing_rejects_unexpected_runtime_kwargs() -> None:
-    @tool
-    async def echo(message: str) -> str:
-        """Echo."""
-        return message
-
-    with pytest.raises(TypeError, match="Unexpected keyword argument"):
-        await echo.invoke(arguments={"message": "hi"}, skip_parsing=True, api_token="secret")
-
-
-async def test_invoke_skip_parsing_raises_for_declaration_only_tool() -> None:
-    declared = FunctionTool(name="dummy", description="declaration only")
-
-    from agent_framework.exceptions import ToolException
-
-    with pytest.raises(ToolException):
-        await declared.invoke(arguments={}, skip_parsing=True)
-
-
-async def test_invoke_skip_parsing_records_telemetry(span_exporter: InMemorySpanExporter) -> None:
-    """skip_parsing participates in OTEL spans and records str(raw) as TOOL_RESULT."""
-
-    @tool(name="raw_tool", description="raw tool")
-    def returns_dict(x: int) -> dict[str, int]:
-        """Returns a dict."""
-        return {"value": x}
-
-    span_exporter.clear()
-    raw = await returns_dict.invoke(arguments={"x": 5}, tool_call_id="raw_call", skip_parsing=True)
-
-    assert raw == {"value": 5}
-    spans = span_exporter.get_finished_spans()
-    assert len(spans) == 1
-    span = spans[0]
-    assert span.attributes[OtelAttr.TOOL_NAME] == "raw_tool"
-    assert span.attributes[OtelAttr.TOOL_CALL_ID] == "raw_call"
-    assert span.attributes[OtelAttr.TOOL_RESULT] == "{'value': 5}"
-
-
-async def test_invoke_default_path_records_parsed_telemetry(
-    span_exporter: InMemorySpanExporter,
-) -> None:
-    """Regression: omitting skip_parsing still records the parsed result in telemetry."""
-
-    def parser(value: Any) -> str:
-        return f"parsed:{value}"
-
-    @tool(name="parsed_tool", description="parsed", result_parser=parser)
-    def returns_int() -> int:
-        """Returns an int."""
-        return 7
-
-    span_exporter.clear()
-    parsed = await returns_int.invoke(tool_call_id="parsed_call")
-
-    assert parsed[0].text == "parsed:7"
-    spans = span_exporter.get_finished_spans()
-    assert len(spans) == 1
-    assert spans[0].attributes[OtelAttr.TOOL_RESULT] == "parsed:7"
-
-
-def test_skip_parsing_is_singleton() -> None:
-    """SKIP_PARSING is a singleton; instantiation returns the same object."""
-    from agent_framework._tools import _SkipParsingSentinel
-
-    assert _SkipParsingSentinel() is SKIP_PARSING
-    assert repr(SKIP_PARSING) == "SKIP_PARSING"
-
-
 # endregion
@@ -4,7 +4,7 @@ description = "Declarative specification support for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -22,7 +22,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
    "powerfx>=0.0.32,<0.0.35; python_version < '3.14'",
    "pyyaml>=6.0,<7.0",
 ]
@@ -4,7 +4,7 @@ description = "Debug UI for Microsoft Agent Framework with OpenAI-compatible API
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://github.com/microsoft/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-     "agent-framework-core>=1.1.1,<2",
+     "agent-framework-core>=1.1.0,<2",
     "openai>=1.99.0,<3",
     "opentelemetry-sdk>=1.39.0,<2",
     "fastapi>=0.115.0,<0.133.1",
@@ -4,7 +4,7 @@ description = "Durable Task integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -22,7 +22,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
    "durabletask>=1.3.0,<2",
    "durabletask-azuremanaged>=1.3.0,<2",
    "python-dateutil>=2.8.0,<3",
@@ -455,18 +455,8 @@ class RawFoundryChatClient(  # type: ignore[misc]

        Returns:
            An MCPTool configuration ready to pass to an Agent.
-
-        Raises:
-            ValueError: If neither ``url`` nor ``project_connection_id`` is supplied
-                — one is required by the Foundry Responses API.
        """
-        if not url and not project_connection_id:
-            raise ValueError("MCP tool requires either 'url' or 'project_connection_id' to be specified.")
-
-        mcp_kwargs: dict[str, Any] = {"server_label": name.replace(" ", "_"), **kwargs}
-        if url:
-            mcp_kwargs["server_url"] = url
-        mcp = FoundryMCPTool(**mcp_kwargs)
+        mcp = FoundryMCPTool(server_label=name.replace(" ", "_"), server_url=url or "", **kwargs)

        if description:
            mcp["server_description"] = description
@@ -133,55 +133,26 @@ def select_toolbox_tools(
    return selected


-def _validate_hosted_tool_payload(sanitized: Mapping[str, Any]) -> None:
-    """Fail fast on hosted tool payloads that would always be rejected by the Responses API.
-
-    These mismatches are not injectable defaults — the caller must supply the
-    missing information — so surfacing a clear error here points at the toolbox
-    definition instead of letting the API return a generic 400.
-    """
-    tool_type = sanitized.get("type")
-    if tool_type == "file_search" and not sanitized.get("vector_store_ids"):
-        raise ValueError(
-            "'file_search' tool is missing required 'vector_store_ids'. "
-            "If this came from a Foundry toolbox, update the toolbox definition "
-            "to include at least one vector store ID."
-        )
-    if tool_type == "mcp" and not sanitized.get("server_url") and not sanitized.get("project_connection_id"):
-        raise ValueError(
-            "'mcp' tool is missing both 'server_url' and 'project_connection_id'. "
-            "If this came from a Foundry toolbox, update the toolbox definition "
-            "to include one of these."
-        )
-
-
@experimental(feature_id=ExperimentalFeature.TOOLBOXES)
 def sanitize_foundry_response_tool(tool_item: Any) -> Any:
    """Return a Responses-API-safe tool payload for Foundry hosted tools.

-    Reconciles known mismatches between toolbox reads and the Responses API:
+    Azure AI Projects toolbox reads can currently return hosted tool objects with
+    extra read-model decoration fields such as top-level ``name`` and
+    ``description``. Azure AI Foundry rejects at least ``name`` on Responses API
+    requests with:

-    1. Toolbox reads can return hosted tool objects decorated with read-model
-       fields such as top-level ``name`` and ``description``. The Responses API
-       rejects at least ``name`` with ``Unknown parameter: 'tools[0].name'``.
-       These fields are stripped from non-function hosted tool payloads.
-    2. ``code_interpreter`` tools stored in a toolbox without a ``container``
-       field (the Azure SDK treats it as optional) are rejected by the Responses
-       API with ``Missing required parameter: 'tools[N].container'``. A default
-       ``{"type": "auto"}`` container is injected when absent.
-    3. Hosted tools that are structurally incomplete in ways that cannot be
-       defaulted (``file_search`` without ``vector_store_ids``, ``mcp`` without
-       either ``server_url`` or ``project_connection_id``) raise ``ValueError``
-       with a message that points at the toolbox definition.
+    ``Unknown parameter: 'tools[0].name'``.

-    These are workarounds until the toolbox/Responses proxy normalizes payloads
-    server-side.
+    We defensively strip these decoration fields for non-function hosted tools so
+    the round-trip
+    ``toolbox.tools -> Agent(..., tools=...) -> run()`` works, while the Azure
+    SDK/service behavior is corrected upstream.
    """
    if isinstance(tool_item, FoundryMCPTool):
        sanitized: dict[str, Any] = dict(cast("Mapping[str, Any]", tool_item))
        sanitized.pop("name", None)
        sanitized.pop("description", None)
-        _validate_hosted_tool_payload(sanitized)
        return sanitized

    if isinstance(tool_item, Mapping):
@@ -190,9 +161,6 @@ def sanitize_foundry_response_tool(tool_item: Any) -> Any:
            sanitized = dict(mapping)
            sanitized.pop("name", None)
            sanitized.pop("description", None)
-            if sanitized.get("type") == "code_interpreter" and "container" not in sanitized:
-                sanitized["container"] = {"type": "auto"}
-            _validate_hosted_tool_payload(sanitized)
            return sanitized

    return cast(Any, tool_item)
@@ -4,7 +4,7 @@ description = "Microsoft Foundry integrations for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.1.1"
+version = "1.1.0"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
    "agent-framework-openai>=1.1.0,<2",
    "azure-ai-inference>=1.0.0b9,<1.0.0b10",
    "azure-ai-projects>=2.1.0,<3.0",
@@ -607,14 +607,6 @@ def test_get_mcp_tool_with_project_connection_id() -> None:
    assert tool_config["project_connection_id"] == "conn-123"
    assert tool_config["allowed_tools"] == ["search_docs"]
    assert tool_config["server_label"] == "Docs_MCP"
-    # ``server_url`` should not be fabricated when only a project connection is supplied.
-    assert "server_url" not in tool_config
-
-
-def test_get_mcp_tool_requires_url_or_project_connection_id() -> None:
-    """Missing both ``url`` and ``project_connection_id`` is always invalid."""
-    with pytest.raises(ValueError, match="url.*project_connection_id"):
-        FoundryChatClient.get_mcp_tool(name="x")


 def test_prepare_tools_for_openai_strips_extraneous_name_from_foundry_mcp_tool() -> None:
@@ -663,103 +655,6 @@ def test_prepare_tools_for_openai_strips_read_model_fields_from_toolbox_code_int
    assert "description" not in prepared


-def test_prepare_tools_for_openai_injects_default_container_for_code_interpreter_dict() -> None:
-    """Toolbox-returned code_interpreter without a container must get a default injected.
-
-    The Azure SDK treats ``container`` as optional, but the Responses API rejects
-    ``code_interpreter`` entries without one. The sanitizer backfills ``{"type": "auto"}``.
-    """
-    project_client = MagicMock()
-    project_client.get_openai_client.return_value = _make_mock_openai_client()
-    client = FoundryChatClient(project_client=project_client, model="test-model")
-
-    tool = {
-        "type": "code_interpreter",
-        "name": "code_interpreter_t6bbtm",
-    }
-
-    response_tools = client._prepare_tools_for_openai([tool])
-
-    assert len(response_tools) == 1
-    prepared = response_tools[0]
-    assert prepared["type"] == "code_interpreter"
-    assert prepared["container"] == {"type": "auto"}
-    assert "name" not in prepared
-
-
-def test_prepare_tools_for_openai_injects_default_container_for_code_interpreter_sdk_instance() -> None:
-    """SDK ``CodeInterpreterTool`` instances without a container must also be backfilled.
-
-    Reproduces the toolbox creation path that calls
-    ``CodeInterpreterTool(name="code_interpreter")`` without a container.
-    """
-    from azure.ai.projects.models import CodeInterpreterTool
-
-    project_client = MagicMock()
-    project_client.get_openai_client.return_value = _make_mock_openai_client()
-    client = FoundryChatClient(project_client=project_client, model="test-model")
-
-    response_tools = client._prepare_tools_for_openai([CodeInterpreterTool(name="code_interpreter")])
-
-    assert len(response_tools) == 1
-    prepared = response_tools[0]
-    assert prepared["type"] == "code_interpreter"
-    assert prepared["container"] == {"type": "auto"}
-    assert "name" not in prepared
-
-
-def test_prepare_tools_for_openai_preserves_existing_code_interpreter_container() -> None:
-    """An already-populated container must not be overwritten by the sanitizer."""
-    project_client = MagicMock()
-    project_client.get_openai_client.return_value = _make_mock_openai_client()
-    client = FoundryChatClient(project_client=project_client, model="test-model")
-
-    explicit_container = {"file_ids": ["file_123"], "type": "auto"}
-    tool = {"type": "code_interpreter", "container": explicit_container}
-
-    response_tools = client._prepare_tools_for_openai([tool])
-
-    assert response_tools[0]["container"] == explicit_container
-
-
-def test_prepare_tools_for_openai_rejects_file_search_without_vector_store_ids() -> None:
-    """``file_search`` without ``vector_store_ids`` is always invalid — surface a clear error."""
-    project_client = MagicMock()
-    project_client.get_openai_client.return_value = _make_mock_openai_client()
-    client = FoundryChatClient(project_client=project_client, model="test-model")
-
-    with pytest.raises(ValueError, match="vector_store_ids"):
-        client._prepare_tools_for_openai([{"type": "file_search", "name": "fs"}])
-
-
-def test_prepare_tools_for_openai_rejects_mcp_without_server_destination() -> None:
-    """``mcp`` with neither ``server_url`` nor ``project_connection_id`` is always invalid."""
-    project_client = MagicMock()
-    project_client.get_openai_client.return_value = _make_mock_openai_client()
-    client = FoundryChatClient(project_client=project_client, model="test-model")
-
-    tool = FoundryMCPTool(server_label="orphan")
-
-    with pytest.raises(ValueError, match="server_url.*project_connection_id"):
-        client._prepare_tools_for_openai([tool])
-
-
-def test_prepare_tools_for_openai_accepts_mcp_with_only_project_connection_id() -> None:
-    """MCP tools backed by a Foundry connection (no ``server_url``) must still pass validation."""
-    project_client = MagicMock()
-    project_client.get_openai_client.return_value = _make_mock_openai_client()
-    client = FoundryChatClient(project_client=project_client, model="test-model")
-
-    tool = FoundryMCPTool(server_label="githubmcp")
-    tool["project_connection_id"] = "githubmcp"
-
-    response_tools = client._prepare_tools_for_openai([tool])
-
-    assert len(response_tools) == 1
-    assert response_tools[0]["project_connection_id"] == "githubmcp"
-    assert "server_url" not in response_tools[0]
-
-
 def test_prepare_tools_for_openai_strips_name_from_non_function_hosted_tool_dicts() -> None:
    """All non-function hosted tool payloads should drop top-level read-model names."""
    project_client = MagicMock()
@@ -4,7 +4,7 @@ description = "Foundry Hosting integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0a260423"
+version = "1.0.0a260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -12,7 +12,7 @@ urls.release_notes = "https://github.com/microsoft/agent-framework/releases?q=ta
 urls.issues = "https://github.com/microsoft/agent-framework/issues"
 classifiers = [
  "License :: OSI Approved :: MIT License",
-  "Development Status :: 3 - Alpha",
+  "Development Status :: 4 - Alpha",
  "Intended Audience :: Developers",
  "Programming Language :: Python :: 3",
  "Programming Language :: Python :: 3.10",
@@ -23,7 +23,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
    "azure-ai-agentserver-core==2.0.0b2",
    "azure-ai-agentserver-responses==1.0.0b4",
    "azure-ai-agentserver-invocations==1.0.0b2",
@@ -4,7 +4,7 @@ description = "Foundry Local integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
    "agent-framework-openai>=1.1.0,<2",
    "foundry-local-sdk>=0.5.1,<0.5.2",
 ]
@@ -4,7 +4,7 @@ description = "Google Gemini integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0a260423"
+version = "1.0.0a260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -24,7 +24,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2.0",
+    "agent-framework-core>=1.1.0,<2.0",
    "google-genai>=1.0.0,<2.0.0",
 ]

@@ -4,7 +4,7 @@ description = "GitHub Copilot integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
    "github-copilot-sdk>=0.2.1,<=0.2.1; python_version >= '3.11'",
 ]

@@ -130,9 +130,3 @@ codeact = HyperlightCodeActProvider(
 - `allowed_domains` accepts a single string target such as `"github.com"` to
  allow all backend-supported methods, an explicit `(target, method_or_methods)`
  tuple such as `("github.com", "GET")`, or an `AllowedDomain` named tuple.
- Tools registered with the sandbox return their native Python value
-  (`dict`, `list`, primitives, or custom objects) directly to the guest via the
-  Hyperlight FFI. Any `result_parser` configured on a `FunctionTool` is
-  intended for LLM-facing consumers and does not run on the sandbox path —
-  apply formatting inside the tool function itself if you need it for
-  in-sandbox consumers.
@@ -2,45 +2,42 @@

 from __future__ import annotations

+import ast
 import asyncio
+import copy
 import mimetypes
 import shutil
 import threading
 import time
 from collections.abc import Callable, Sequence
-from concurrent.futures import Future, ThreadPoolExecutor
-from contextlib import suppress
-from copy import copy
-from dataclasses import dataclass, field
+from dataclasses import dataclass
 from pathlib import Path, PurePosixPath
 from tempfile import TemporaryDirectory
-from typing import Any, Protocol, TypeGuard, TypeVar, cast
+from typing import Annotated, Any, Protocol, TypeGuard, cast
 from urllib.parse import urlparse

 from agent_framework import Content, FunctionTool
 from agent_framework._tools import ApprovalMode, normalize_tools
+from pydantic import BaseModel, Field

 from ._instructions import build_codeact_instructions, build_execute_code_description
 from ._types import AllowedDomain, AllowedDomainInput, FileMount, FileMountHostPath, FileMountInput

 DEFAULT_HYPERLIGHT_BACKEND = "wasm"
 DEFAULT_HYPERLIGHT_MODULE = "python_guest.path"
-EXECUTE_CODE_TOOL_DESCRIPTION = "Execute Python in an isolated Hyperlight sandbox."
+EXECUTE_CODE_INPUT_DESCRIPTION = "Python code to execute in an isolated Hyperlight sandbox."
 OUTPUT_FILE_RETRY_ATTEMPTS = 10
 OUTPUT_FILE_RETRY_DELAY_SECONDS = 0.1

-EXECUTE_CODE_INPUT_SCHEMA: dict[str, Any] = {
-    "type": "object",
-    "title": "_ExecuteCodeInput",
-    "properties": {
-        "code": {
-            "type": "string",
-            "title": "Code",
-            "description": "Python code to execute in an isolated Hyperlight sandbox.",
-        },
-    },
-    "required": ["code"],
-}
+
+class _ExecuteCodeInput(BaseModel):
+    code: Annotated[str, Field(description=EXECUTE_CODE_INPUT_DESCRIPTION)]
+
+
+@dataclass(frozen=True, slots=True)
+class _StoredFileMount:
+    host_path: Path
+    mount_path: str


@dataclass(frozen=True, slots=True)
@@ -88,43 +85,13 @@ class SandboxRuntime(Protocol):
    def execute(self, *, config: _RunConfig, code: str) -> list[Content]: ...


-_T = TypeVar("_T")
-
-
-class _SandboxWorker:
-    """Single-threaded executor that confines all sandbox operations to one OS thread.
-
-    The Hyperlight ``WasmSandbox`` is declared ``unsendable`` in PyO3, meaning it can only be
-    accessed from the OS thread that created it; touching it from any other thread triggers a
-    Rust panic that cannot be caught from Python. Every cached :class:`_SandboxEntry` therefore
-    owns its own ``_SandboxWorker``, and *all* lifecycle and execution calls against the
-    underlying sandbox object must be routed through :meth:`submit`/:meth:`run`.
-    """
-
-    __slots__ = ("_executor",)
-
-    def __init__(self, *, name: str = "hl-sandbox") -> None:
-        self._executor = ThreadPoolExecutor(max_workers=1, thread_name_prefix=name)
-
-    def submit(self, fn: Callable[..., _T], /, *args: Any, **kwargs: Any) -> Future[_T]:
-        return self._executor.submit(fn, *args, **kwargs)
-
-    def run(self, fn: Callable[..., _T], /, *args: Any, **kwargs: Any) -> _T:
-        return self._executor.submit(fn, *args, **kwargs).result()
-
-    def shutdown(self) -> None:
-        # Do not block on shutdown; stop accepting new tasks, but allow the currently running
-        # task and any already-queued tasks to finish before the worker thread exits.
-        self._executor.shutdown(wait=False, cancel_futures=False)
-
-
@dataclass
 class _SandboxEntry:
    sandbox: Any
    snapshot: Any
    input_dir: TemporaryDirectory[str] | None
    output_dir: TemporaryDirectory[str] | None
-    worker: _SandboxWorker = field(default_factory=_SandboxWorker)
+    lock: threading.RLock


 def _load_sandbox_class() -> type[Any]:
@@ -139,6 +106,10 @@ def _load_sandbox_class() -> type[Any]:
    return Sandbox


+def _passthrough_result_parser(result: Any) -> str:
+    return repr(result)
+
+
 def _collect_tools(*tool_groups: Any) -> list[FunctionTool]:
    tools_by_name: dict[str, FunctionTool] = {}

@@ -195,7 +166,7 @@ def _is_file_mount_pair(value: Any) -> TypeGuard[FileMount | tuple[FileMountHost
    return isinstance(host_path, (str, Path)) and isinstance(mount_path, str)


-def _normalize_file_mount_input(file_mount: FileMountInput) -> FileMount:
+def _normalize_file_mount_input(file_mount: FileMountInput) -> _StoredFileMount:
    host_path: FileMountHostPath
    mount_path: str
    if isinstance(file_mount, str):
@@ -205,7 +176,7 @@ def _normalize_file_mount_input(file_mount: FileMountInput) -> FileMount:
        host_path = file_mount[0]
        mount_path = file_mount[1]

-    return FileMount(
+    return _StoredFileMount(
        host_path=_resolve_existing_path(host_path),
        mount_path=_normalize_mount_path(mount_path),
    )
@@ -474,13 +445,18 @@ def _build_execution_contents(


 def _make_sandbox_callback(tool_obj: FunctionTool) -> Callable[..., Any]:
-    sandbox_tool = copy(tool_obj)
+    sandbox_tool = copy.copy(tool_obj)
+    # Auto-assign a passthrough parser so the raw return value round-trips through
+    # `ast.literal_eval` in the sandbox callback below. User-supplied parsers are
+    # left in place so callers can customize how results are exposed to the guest.
+    if sandbox_tool.result_parser is None:
+        sandbox_tool.result_parser = _passthrough_result_parser

    def _callback(**kwargs: Any) -> Any:
-        async def _invoke() -> Any:
-            return await sandbox_tool.invoke(arguments=kwargs, skip_parsing=True)
+        async def _invoke() -> list[Content]:
+            return await sandbox_tool.invoke(arguments=kwargs)

-        # FunctionTool.invoke() is async. The real Hyperlight backend invokes
+        # FunctionTool.invoke() is always async. The real Hyperlight backend invokes
        # registered callbacks synchronously via FFI, so this must be a sync function.
        # We run the async call on a dedicated thread to avoid conflicts with any
        # event loop that may be running on the current thread.
@@ -498,11 +474,22 @@ def _make_sandbox_callback(tool_obj: FunctionTool) -> Callable[..., Any]:
        worker.join()
        if error_box:
            raise error_box[0]
-        # Return the raw value. The Hyperlight FFI marshals primitives (dict, list,
-        # str, int, float, bool, None) natively into the guest, and falls back to
-        # repr()/str() for unsupported types — so the guest receives real Python
-        # objects without a lossy host-side serialization round-trip.
-        return result_box[0]
+        contents: list[Content] = result_box[0]
+
+        values: list[Any] = []
+        for content in contents:
+            if content.type == "text" and content.text is not None:
+                try:
+                    values.append(ast.literal_eval(content.text))
+                except (SyntaxError, ValueError):
+                    values.append(content.text)
+                continue
+
+            values.append(content.to_dict())
+
+        if len(values) == 1:
+            return values[0]
+        return values

    return _callback

@@ -522,7 +509,7 @@ def _clear_directory(output_dir: TemporaryDirectory[str] | None) -> None:
            pass


-class _SandboxRegistry(SandboxRuntime):
+class _SandboxRegistry:
    def __init__(self) -> None:
        self._entries: dict[tuple[Any, ...], _SandboxEntry] = {}
        self._entries_lock = threading.RLock()
@@ -530,54 +517,28 @@ class _SandboxRegistry(SandboxRuntime):
    def execute(self, *, config: _RunConfig, code: str) -> list[Content]:
        """Execute code in a cached sandbox matching the given config.

-        Entries are keyed by ``config.cache_key()``. All operations against the underlying
-        sandbox object are routed through the entry's dedicated single-threaded worker, which
-        both serializes concurrent callers and satisfies the PyO3 ``unsendable`` invariant
-        that the sandbox can only be touched from the thread that created it.
+        Entries are keyed by ``config.cache_key()``. Concurrent calls with the same
+        key are serialized by the entry lock so they never race, but they share the
+        same sandbox instance. For true parallel execution, use distinct provider
+        instances or configs that produce different cache keys.
        """
-        entry = self._get_or_create_entry(config)
-        return entry.worker.run(self._run_on_worker, entry, code)
-
-    @staticmethod
-    def _run_on_worker(entry: _SandboxEntry, code: str) -> list[Content]:
-        entry.sandbox.restore(entry.snapshot)
-        _clear_directory(entry.output_dir)
-        result = entry.sandbox.run(code=code)
-        return _build_execution_contents(
-            result=result,
-            sandbox=entry.sandbox,
-            output_dir=entry.output_dir,
-            code=code,
-        )
-
-    def _get_or_create_entry(self, config: _RunConfig) -> _SandboxEntry:
        cache_key = config.cache_key()
        with self._entries_lock:
            entry = self._entries.get(cache_key)
            if entry is None:
                entry = self._create_entry(config)
                self._entries[cache_key] = entry
-            return entry

-    def close(self) -> None:
-        """Shut down all per-entry worker threads and release per-entry resources.
-
-        Safe to call multiple times. Runs any sandbox close hook on the entry's
-        own worker thread to honor the PyO3 ``unsendable`` invariant.
-        """
-        with self._entries_lock:
-            entries = list(self._entries.values())
-            self._entries.clear()
-        for entry in entries:
-            close_hook = getattr(entry.sandbox, "close", None) or getattr(entry.sandbox, "shutdown", None)
-            if callable(close_hook):
-                with suppress(Exception):
-                    entry.worker.run(close_hook)
-            entry.worker.shutdown()
-            for tmp_dir in (entry.input_dir, entry.output_dir):
-                if tmp_dir is not None:
-                    with suppress(Exception):
-                        tmp_dir.cleanup()
+        with entry.lock:
+            entry.sandbox.restore(entry.snapshot)
+            _clear_directory(entry.output_dir)
+            result = entry.sandbox.run(code=code)
+            return _build_execution_contents(
+                result=result,
+                sandbox=entry.sandbox,
+                output_dir=entry.output_dir,
+                code=code,
+            )

    def _create_entry(self, config: _RunConfig) -> _SandboxEntry:
        input_dir_handle = TemporaryDirectory() if config.filesystem_enabled else None
@@ -617,37 +578,26 @@ class _SandboxRegistry(SandboxRuntime):
                        methods=list(allowed_domain.methods) if allowed_domain.methods is not None else None,
                    )

-        worker = _SandboxWorker()
-
-        def _build_sandbox() -> tuple[Any, Any]:
-            sandbox = _create_sandbox()
-            _configure_sandbox(sandbox=sandbox, expand_missing_scheme=False)
-
-            try:
-                sandbox.run("None")
-            except RuntimeError as exc:
-                if not _should_retry_allowed_domain_registration(error=exc, allowed_domains=config.allowed_domains):
-                    raise
-
-                sandbox = _create_sandbox()
-                _configure_sandbox(sandbox=sandbox, expand_missing_scheme=True)
-                sandbox.run("None")
-
-            snapshot = sandbox.snapshot()
-            return sandbox, snapshot
+        sandbox = _create_sandbox()
+        _configure_sandbox(sandbox=sandbox, expand_missing_scheme=False)

        try:
-            sandbox, snapshot = worker.run(_build_sandbox)
-        except BaseException:
-            worker.shutdown()
-            raise
+            sandbox.run("None")
+        except RuntimeError as exc:
+            if not _should_retry_allowed_domain_registration(error=exc, allowed_domains=config.allowed_domains):
+                raise

+            sandbox = _create_sandbox()
+            _configure_sandbox(sandbox=sandbox, expand_missing_scheme=True)
+            sandbox.run("None")
+
+        snapshot = sandbox.snapshot()
        return _SandboxEntry(
            sandbox=sandbox,
            snapshot=snapshot,
            input_dir=input_dir_handle,
            output_dir=output_dir_handle,
-            worker=worker,
+            lock=threading.RLock(),
        )


@@ -669,10 +619,10 @@ class HyperlightExecuteCodeTool(FunctionTool):
    ) -> None:
        super().__init__(
            name="execute_code",
-            description=EXECUTE_CODE_TOOL_DESCRIPTION,
+            description=EXECUTE_CODE_INPUT_DESCRIPTION,
            approval_mode="never_require",
            func=self._run_code,
-            input_model=EXECUTE_CODE_INPUT_SCHEMA,
+            input_model=_ExecuteCodeInput,
        )
        self._state_lock = threading.RLock()
        self._registry = _registry or _SandboxRegistry()
@@ -682,7 +632,7 @@ class HyperlightExecuteCodeTool(FunctionTool):
        self._module: str | None = module
        self._module_path: str | None = module_path
        self._managed_tools: list[FunctionTool] = []
-        self._file_mounts: dict[str, FileMount] = {}
+        self._file_mounts: dict[str, _StoredFileMount] = {}
        self._allowed_domains: dict[str, AllowedDomain] = {}

        if tools is not None:
@@ -698,7 +648,7 @@ class HyperlightExecuteCodeTool(FunctionTool):
    def description(self) -> str:
        state_lock = getattr(self, "_state_lock", None)
        if state_lock is None:
-            return str(self.__dict__.get("description", EXECUTE_CODE_TOOL_DESCRIPTION))
+            return str(self.__dict__.get("description", EXECUTE_CODE_INPUT_DESCRIPTION))

        with state_lock:
            allowed_domains = sorted(self._allowed_domains.values(), key=lambda value: value.target)
@@ -891,9 +841,9 @@ class HyperlightExecuteCodeTool(FunctionTool):
        workspace_signature = _path_tree_signature(workspace_root) if workspace_root is not None else ()
        normalized_mounts = tuple(
            _NormalizedFileMount(
-                host_path=Path(mount.host_path),
+                host_path=mount.host_path,
                mount_path=mount.mount_path,
-                path_signature=_path_tree_signature(Path(mount.host_path)),
+                path_signature=_path_tree_signature(mount.host_path),
            )
            for mount in stored_mounts
        )
@@ -4,7 +4,7 @@ description = "Hyperlight CodeAct integrations for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0a260423"
+version = "1.0.0a260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -22,7 +22,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
    "hyperlight-sandbox>=0.3.0,<0.4",
    "hyperlight-sandbox-backend-wasm>=0.3.0,<0.4 ; ((sys_platform == 'linux' and platform_machine == 'x86_64') or (sys_platform == 'win32' and platform_machine == 'AMD64')) and python_version < '3.14'",
    "hyperlight-sandbox-python-guest>=0.3.0,<0.4",
@@ -937,191 +937,3 @@ async def test_run_code_does_not_block_event_loop() -> None:

    assert concurrent_ran, "Event loop was blocked during sandbox execution"
    assert result[0].type == "text"
-
-
-class _ThreadAffinityFakeSandbox(_FakeSandbox):
-    """Fake sandbox that records the OS thread of every method invocation.
-
-    Mirrors the PyO3 ``unsendable`` invariant of ``hyperlight_sandbox.WasmSandbox``:
-    if ``__init__``, ``register_tool``, ``allow_domain``, ``run``, ``snapshot`` or ``restore``
-    are ever called from more than one thread for a given instance, the test fails.
-    """
-
-    affinity_failures: list[str] = []
-
-    def __init__(self, **kwargs: Any) -> None:
-        super().__init__(**kwargs)
-        self._owner_thread = threading.get_ident()
-        self.thread_ids: set[int] = {self._owner_thread}
-
-    def _record(self, method: str) -> None:
-        ident = threading.get_ident()
-        self.thread_ids.add(ident)
-        if ident != self._owner_thread:
-            _ThreadAffinityFakeSandbox.affinity_failures.append(
-                f"{method} called from thread {ident}, expected {self._owner_thread}"
-            )
-
-    def register_tool(self, name_or_tool: Any, callback: Any | None = None) -> None:
-        self._record("register_tool")
-        super().register_tool(name_or_tool, callback)
-
-    def allow_domain(self, target: str, methods: list[str] | None = None) -> None:
-        self._record("allow_domain")
-        super().allow_domain(target, methods)
-
-    def run(self, code: str) -> _FakeResult:
-        self._record("run")
-        return super().run(code)
-
-    def snapshot(self) -> str:
-        self._record("snapshot")
-        return super().snapshot()
-
-    def restore(self, snapshot: Any) -> None:
-        self._record("restore")
-        super().restore(snapshot)
-
-
-async def test_sandbox_calls_are_pinned_to_owning_worker_thread(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    """Regression: WasmSandbox is unsendable; every sandbox call must run on its owner thread."""
-    _ThreadAffinityFakeSandbox.instances.clear()
-    _ThreadAffinityFakeSandbox.affinity_failures.clear()
-    monkeypatch.setattr(execute_code_module, "_load_sandbox_class", lambda: _ThreadAffinityFakeSandbox)
-
-    execute_code = HyperlightExecuteCodeTool()
-
-    # Invoke many times concurrently; asyncio.to_thread will spread these across the default
-    # executor's worker threads, which previously caused PyO3 to panic when a different thread
-    # touched the cached sandbox.
-    results = await asyncio.gather(*[execute_code.invoke(arguments={"code": "None"}) for _ in range(8)])
-    for result in results:
-        assert result[0].type == "text"
-
-    assert _ThreadAffinityFakeSandbox.affinity_failures == []
-    assert len(_ThreadAffinityFakeSandbox.instances) == 1
-    sandbox = _ThreadAffinityFakeSandbox.instances[0]
-    # All sandbox-touching calls must have stayed on a single owning thread, distinct from the
-    # caller thread that asyncio.to_thread used for dispatch.
-    assert sandbox.thread_ids == {sandbox._owner_thread}
-    assert sandbox._owner_thread != threading.get_ident()
-
-
-async def test_sandbox_owner_thread_persists_across_dispatch_threads(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    """Sequential calls landing on different dispatch threads still share one sandbox thread."""
-    _ThreadAffinityFakeSandbox.instances.clear()
-    _ThreadAffinityFakeSandbox.affinity_failures.clear()
-    monkeypatch.setattr(execute_code_module, "_load_sandbox_class", lambda: _ThreadAffinityFakeSandbox)
-
-    execute_code = HyperlightExecuteCodeTool()
-
-    for _ in range(5):
-        result = await execute_code.invoke(arguments={"code": "None"})
-        assert result[0].type == "text"
-
-    assert _ThreadAffinityFakeSandbox.affinity_failures == []
-    assert len(_ThreadAffinityFakeSandbox.instances) == 1
-
-
-def test_sandbox_registry_close_shuts_down_workers(monkeypatch: pytest.MonkeyPatch) -> None:
-    _FakeSandbox.instances.clear()
-    monkeypatch.setattr(execute_code_module, "_load_sandbox_class", lambda: _FakeSandbox)
-
-    registry = execute_code_module._SandboxRegistry()
-    execute_code = HyperlightExecuteCodeTool(_registry=registry)
-    asyncio.run(execute_code.invoke(arguments={"code": "None"}))
-
-    entries = list(registry._entries.values())
-    assert len(entries) == 1
-    worker = entries[0].worker
-
-    registry.close()
-
-    assert registry._entries == {}
-    # Submitting after shutdown must fail; this proves the executor was actually torn down.
-    with pytest.raises(RuntimeError):
-        worker.submit(lambda: None)
-
-
-def test_sandbox_registry_close_releases_per_entry_resources(monkeypatch: pytest.MonkeyPatch, tmp_path: Path) -> None:
-    """close() must invoke any sandbox close hook and release temp directories."""
-
-    close_calls: list[int] = []
-
-    class _ClosableFakeSandbox(_FakeSandbox):
-        def close(self) -> None:
-            close_calls.append(1)
-
-    _FakeSandbox.instances.clear()
-    monkeypatch.setattr(execute_code_module, "_load_sandbox_class", lambda: _ClosableFakeSandbox)
-
-    workspace = tmp_path / "workspace"
-    workspace.mkdir()
-    registry = execute_code_module._SandboxRegistry()
-    execute_code = HyperlightExecuteCodeTool(workspace_root=workspace, _registry=registry)
-    asyncio.run(execute_code.invoke(arguments={"code": "None"}))
-
-    entries = list(registry._entries.values())
-    assert len(entries) == 1
-    entry = entries[0]
-    assert entry.input_dir is not None and entry.output_dir is not None
-    input_path = Path(entry.input_dir.name)
-    output_path = Path(entry.output_dir.name)
-    assert input_path.exists() and output_path.exists()
-
-    registry.close()
-
-    assert close_calls == [1]
-    assert not input_path.exists()
-    assert not output_path.exists()
-
-
-async def test_make_sandbox_callback_returns_native_dict() -> None:
-    """Host tool returning a dict must be forwarded as a native dict (no repr round-trip)."""
-
-    @tool
-    def get_weather(city: str) -> dict[str, Any]:
-        """Get weather."""
-        return {"city": city, "temp_c": 21.5}
-
-    callback = execute_code_module._make_sandbox_callback(get_weather)
-    result = callback(city="Seattle")
-
-    assert isinstance(result, dict)
-    assert result == {"city": "Seattle", "temp_c": 21.5}
-
-
-async def test_make_sandbox_callback_bypasses_user_result_parser() -> None:
-    """Documented behavior change: result_parser is bypassed in the sandbox path."""
-
-    parser_calls: list[Any] = []
-
-    def parser(value: Any) -> str:
-        parser_calls.append(value)
-        return "PARSED"
-
-    @tool(result_parser=parser)
-    def make_payload() -> dict[str, int]:
-        """Returns a dict."""
-        return {"a": 1, "b": 2}
-
-    callback = execute_code_module._make_sandbox_callback(make_payload)
-    result = callback()
-
-    assert result == {"a": 1, "b": 2}
-    assert parser_calls == [], "result_parser must not run on the sandbox path"
-
-
-async def test_make_sandbox_callback_propagates_exceptions() -> None:
-    @tool
-    def boom(x: int) -> int:
-        """Always fails."""
-        raise RuntimeError("nope")
-
-    callback = execute_code_module._make_sandbox_callback(boom)
-    with pytest.raises(RuntimeError, match="nope"):
-        callback(x=1)
@@ -4,7 +4,7 @@ description = "Experimental modules for Microsoft Agent Framework"
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -22,7 +22,7 @@ classifiers = [
  "Programming Language :: Python :: 3.14",
 ]
 dependencies = [
-  "agent-framework-core>=1.1.1,<2",
+  "agent-framework-core>=1.1.0,<2",
 ]

 [project.optional-dependencies]
@@ -4,7 +4,7 @@ description = "Mem0 integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
    "mem0ai>=1.0.0,<2",
 ]

@@ -4,7 +4,7 @@ description = "Ollama integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://learn.microsoft.com/en-us/agent-framework/"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
    "ollama>=0.5.3,<0.5.4",
 ]

@@ -4,7 +4,7 @@ description = "OpenAI integrations for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.1.1"
+version = "1.1.0"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
    "openai>=1.99.0,<3",
 ]

@@ -4,7 +4,7 @@ description = "Orchestration patterns for Microsoft Agent Framework. Includes Se
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
 ]

 [tool.uv]
@@ -4,7 +4,7 @@ description = "Microsoft Purview (Graph dataSecurityAndGovernance) integration f
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://github.com/microsoft/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -24,7 +24,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
    "azure-core>=1.30.0,<2",
    "httpx>=0.27.0,<0.29",
 ]
@@ -4,7 +4,7 @@ description = "Redis integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core>=1.1.1,<2",
+    "agent-framework-core>=1.1.0,<2",
    "redis>=6.4.0,<7.2.1",
    "redisvl>=0.11.0,<0.16",
    "numpy>=2.2.6,<3"
@@ -4,7 +4,7 @@ description = "Microsoft Agent Framework for building AI Agents with Python. Thi
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.1.1"
+version = "1.1.0"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core[all]==1.1.1",
+    "agent-framework-core[all]==1.1.0",
 ]

 [dependency-groups]
@@ -42,12 +42,11 @@ def create_sample_toolbox(name: str) -> str:
    Toolboxes are normally configured in the Foundry portal or a deployment
    script, not the application itself. This helper exists so the samples can
    be run end-to-end without first setting a toolbox up by hand — delete any
-    existing toolbox under ``name``, then create a fresh version containing an
-    MCP tool, a web search tool, and a code interpreter tool. Returns the
-    created version identifier.
+    existing toolbox under ``name``, then create a fresh version containing a
+    single MCP tool. Returns the created version identifier.
    """
    from azure.ai.projects import AIProjectClient
-    from azure.ai.projects.models import CodeInterpreterTool, MCPTool, Tool, WebSearchTool
+    from azure.ai.projects.models import MCPTool, Tool
    from azure.core.exceptions import ResourceNotFoundError

    with (
@@ -68,9 +67,6 @@ def create_sample_toolbox(name: str) -> str:
            )
        ]

-        tools.append(WebSearchTool(name="web_search"))
-        tools.append(CodeInterpreterTool(name="code_interpreter"))
-
        created = project_client.beta.toolboxes.create_version(
            name=name,
            description="Toolbox version with MCP require_approval set to 'never'.",
@@ -3,7 +3,6 @@
 import os
 import subprocess
 from random import randint
-from typing import Annotated

 from agent_framework import Agent, tool
 from agent_framework.foundry import FoundryChatClient
@@ -11,6 +10,7 @@ from agent_framework_foundry_hosting import ResponsesHostServer
 from azure.identity import AzureCliCredential
 from dotenv import load_dotenv
 from pydantic import Field
+from typing import Annotated

 # Load environment variables from .env file
 load_dotenv()
@@ -1,11 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-"""Flaky test report aggregation and trend generation.
-
-Parses JUnit XML (``pytest.xml``) files produced by each CI job, merges
-them with historical data, and generates a markdown trend report showing
-per-test status across the last N runs.
-
-Usage:
-    uv run python -m scripts.flaky_report <reports-dir> <history-file> <output-file>
-"""
@@ -1,20 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-"""CLI entry point for the flaky test report tool.
-
-Usage:
-    uv run python -m scripts.flaky_report <reports-dir> <history-file> <output-file>
-
-Example (from python/ directory):
-    uv run python -m scripts.flaky_report \\
-        ../flaky-reports/ \\
-        flaky-report-history.json \\
-        flaky-test-report.md
-"""
-
-import sys
-
-from scripts.flaky_report.aggregate import main
-
-if __name__ == "__main__":
-    sys.exit(main())
@@ -1,396 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-"""Aggregate per-provider JUnit XML test results and generate a trend report.
-
-Parses ``pytest.xml`` (JUnit XML) files produced by each CI job, merges them
-into a single run, combines with historical data, and generates a markdown
-trend table — the same pattern used by ``scripts/sample_validation/aggregate.py``.
-
-Usage (from CI):
-    python aggregate.py <reports-dir> <history-file> <output-file>
-
-The reports directory is expected to contain subdirectories named
-``test-results-<provider>/`` each containing a ``pytest.xml`` file
-(created by ``actions/download-artifact``).
-"""
-
-from __future__ import annotations
-
-import json
-import sys
-import xml.etree.ElementTree as ET
-from datetime import datetime, timezone
-from pathlib import Path
-from typing import Any
-
-MAX_HISTORY = 5
-
-STATUS_EMOJI = {
-    "passed": "✅",
-    "failed": "❌",
-    "skipped": "⏭️",
-    "xfailed": "⚠️",
-    "error": "❌",
-}
-
-
-def _format_run_label(timestamp: str) -> str:
-    """Format a timestamp as a compact column label (e.g. '04-16 00:57')."""
-    try:
-        dt = datetime.fromisoformat(timestamp)
-        return dt.strftime("%m-%d %H:%M")
-    except (ValueError, TypeError):
-        return timestamp[:16]
-
-
-def _derive_provider(directory_name: str) -> str:
-    """Derive a provider label from a report directory name.
-
-    ``test-results-openai`` → ``OpenAI``
-    ``test-results-azure-openai`` → ``Azure OpenAI``
-    """
-    raw = directory_name.replace("test-results-", "")
-    known = {
-        "openai": "OpenAI",
-        "azure-openai": "Azure OpenAI",
-        "misc": "Misc (Anthropic, Ollama, MCP)",
-        "functions": "Functions",
-        "foundry": "Foundry",
-        "cosmos": "Cosmos",
-        "unit": "Unit",
-    }
-    if raw in known:
-        return known[raw]
-    parts = raw.split("-")
-    return " ".join(p.capitalize() for p in parts)
-
-
-def _parse_junit_xml(xml_path: Path) -> list[dict[str, str]]:
-    """Parse a JUnit XML file and return a list of test result dicts.
-
-    Each dict has keys: ``nodeid``, ``status``, ``duration``, ``message``.
-    """
-    results: list[dict[str, str]] = []
-    try:
-        tree = ET.parse(xml_path)  # noqa: S314
-    except ET.ParseError as exc:
-        print(f"Warning: failed to parse JUnit XML report '{xml_path}': {exc}", file=sys.stderr)
-        return results
-    root = tree.getroot()
-
-    # Handle both <testsuites><testsuite>... and <testsuite>... layouts
-    testcases: list[ET.Element] = []
-    if root.tag == "testsuites":
-        for suite in root.findall("testsuite"):
-            testcases.extend(suite.findall("testcase"))
-    elif root.tag == "testsuite":
-        testcases = list(root.findall("testcase"))
-
-    for tc in testcases:
-        classname = tc.get("classname", "")
-        name = tc.get("name", "")
-        duration = tc.get("time", "0")
-
-        # Use classname::name as a stable identifier.
-        # pytest writes classname as the dotted module path (possibly including
-        # a test class), e.g. "packages.openai.tests.openai.test_chat_client"
-        # or "packages.openai.tests.openai.test_chat_client.TestClass".
-        nodeid = f"{classname}::{name}" if classname else name
-
-        # Extract module/file name from classname for display context.
-        # pytest writes classname as a dotted path. For tests inside a class
-        # it appends the class name, e.g.:
-        #   "packages.foundry.tests.foundry.test_foundry_embedding_client.TestFoundryEmbeddingIntegration"
-        # We want the file-level module: "test_foundry_embedding_client"
-        if classname:
-            parts = classname.rsplit(".", 2)
-            # If the last segment starts with uppercase it's a class name — take the one before it
-            if len(parts) >= 2 and parts[-1][0:1].isupper():
-                module = parts[-2]
-            else:
-                module = parts[-1]
-        else:
-            module = ""
-
-        # Determine status from child elements
-        failure = tc.find("failure")
-        error = tc.find("error")
-        skipped = tc.find("skipped")
-
-        if failure is not None:
-            status = "failed"
-            message = failure.get("message", "")
-        elif error is not None:
-            status = "error"
-            message = error.get("message", "")
-        elif skipped is not None:
-            # pytest marks xfail as <skipped type="pytest.xfail">
-            skip_type = skipped.get("type", "")
-            status = "xfailed" if "xfail" in skip_type else "skipped"
-            message = skipped.get("message", "")
-        else:
-            status = "passed"
-            message = ""
-
-        results.append({
-            "nodeid": nodeid,
-            "status": status,
-            "duration": duration,
-            "message": message,
-            "module": module,
-        })
-
-    return results
-
-
-# ---------------------------------------------------------------------------
-# Loading
-# ---------------------------------------------------------------------------
-
-
-def load_current_run(reports_dir: Path) -> dict[str, Any]:
-    """Load per-provider JUnit XML reports from the current CI run and merge.
-
-    Args:
-        reports_dir: Directory containing ``test-results-<provider>/`` subdirs.
-
-    Returns:
-        Merged run dict with ``timestamp``, ``summary``, ``results``.
-    """
-    combined_results: dict[str, dict[str, str]] = {}  # nodeid → {status, provider}
-
-    # actions/download-artifact creates: reports_dir/test-results-openai/pytest.xml
-    xml_files: list[tuple[str, Path]] = []
-    if reports_dir.is_dir():
-        for subdir in sorted(reports_dir.iterdir()):
-            if subdir.is_dir():
-                xml_file = subdir / "pytest.xml"
-                if xml_file.exists():
-                    xml_files.append((subdir.name, xml_file))
-
-    if not xml_files:
-        print(f"Warning: No pytest.xml files found in {reports_dir}")
-        return {
-            "timestamp": datetime.now(timezone.utc).isoformat(),
-            "summary": {
-                "total": 0,
-                "passed": 0,
-                "failed": 0,
-                "skipped": 0,
-            },
-            "results": {},
-        }
-
-    for dir_name, xml_file in xml_files:
-        print(f"  Loading: {xml_file}")
-        provider = _derive_provider(dir_name)
-        tests = _parse_junit_xml(xml_file)
-        for test in tests:
-            combined_results[test["nodeid"]] = {
-                "status": test["status"],
-                "provider": provider,
-                "module": test.get("module", ""),
-            }
-
-    # Build summary counts using mutually exclusive status buckets.
-    # Errors are folded into the failed count for display purposes.
-    statuses = [r["status"] for r in combined_results.values()]
-    summary = {
-        "total": len(statuses),
-        "passed": statuses.count("passed"),
-        "failed": statuses.count("failed") + statuses.count("error"),
-        "skipped": statuses.count("skipped"),
-    }
-
-    return {
-        "timestamp": datetime.now(timezone.utc).isoformat(),
-        "summary": summary,
-        "results": combined_results,
-    }
-
-
-def load_history(history_path: Path) -> list[dict[str, Any]]:
-    """Load previous run history from a cache file."""
-    if history_path.exists():
-        with open(history_path, encoding="utf-8") as f:
-            data = json.load(f)
-        runs = data.get("runs", [])
-        print(f"  Loaded {len(runs)} previous run(s) from history")
-        return runs
-    print("  No previous history found")
-    return []
-
-
-def save_history(history_path: Path, runs: list[dict[str, Any]]) -> None:
-    """Save run history, keeping only the last ``MAX_HISTORY`` entries."""
-    history_path.parent.mkdir(parents=True, exist_ok=True)
-    trimmed = runs[-MAX_HISTORY:]
-    with open(history_path, "w", encoding="utf-8") as f:
-        json.dump({"runs": trimmed}, f, indent=2)
-    print(f"  Saved {len(trimmed)} run(s) to history")
-
-
-# ---------------------------------------------------------------------------
-# Report generation
-# ---------------------------------------------------------------------------
-
-
-def _short_name(nodeid: str) -> str:
-    """Extract a short test name from a full nodeid.
-
-    ``packages.openai.tests.openai.test_openai_chat_client::test_integration_options``
-    → ``test_integration_options``
-    """
-    return nodeid.split("::")[-1] if "::" in nodeid else nodeid
-
-
-def generate_trend_report(runs: list[dict[str, Any]]) -> str:
-    """Generate a markdown trend report from run history."""
-    lines = [
-        "# 🔬 Flaky Test Report",
-        "",
-        f"*Generated: {datetime.now(timezone.utc).strftime('%Y-%m-%d %H:%M UTC')}*",
-        "",
-    ]
-
-    # --- Overall status table (most recent first) ---
-    lines.append("## Overall Status (Last 5 Runs)")
-    lines.append("")
-    lines.append("| Run | Total | ✅ Passed | ❌ Failed | ⏭️ Skipped |")
-    lines.append("|-----|-------|-----------|-----------|------------|")
-
-    for run in reversed(runs):
-        s = run.get("summary", {})
-        total = s.get("total", 0)
-        label = _format_run_label(run["timestamp"])
-        lines.append(
-            f"| {label} "
-            f"| {total} "
-            f"| {s.get('passed', 0)}/{total} "
-            f"| {s.get('failed', 0)}/{total} "
-            f"| {s.get('skipped', 0)}/{total} |"
-        )
-
-    for _ in range(MAX_HISTORY - len(runs)):
-        lines.append("| N/A | N/A | N/A | N/A | N/A |")
-
-    lines.append("")
-
-    # --- Per-test results table ---
-    lines.append("## Per-Test Results")
-    lines.append("")
-
-    # Collect all test nodeids, providers, and modules across all runs
-    all_tests: dict[str, str] = {}  # nodeid → provider (from most recent run)
-    all_modules: dict[str, str] = {}  # nodeid → module (from most recent run)
-    for run in runs:
-        for nodeid, info in run.get("results", {}).items():
-            provider = info.get("provider", "Unknown") if isinstance(info, dict) else "Unknown"
-            module = info.get("module", "") if isinstance(info, dict) else ""
-            all_tests[nodeid] = provider
-            all_modules[nodeid] = module
-
-    if not all_tests:
-        lines.append("*No test results available.*")
-        return "\n".join(lines)
-
-    # Build header (most recent run first)
-    header = "| Test | File | Provider |"
-    separator = "|------|------|----------|"
-    for run in reversed(runs):
-        label = _format_run_label(run["timestamp"])
-        header += f" {label} |"
-        separator += "------------|"
-    for _ in range(MAX_HISTORY - len(runs)):
-        header += " N/A |"
-        separator += "-----|"
-
-    lines.append(header)
-    lines.append(separator)
-
-    # Sort by provider then test name
-    for nodeid in sorted(all_tests, key=lambda n: (all_tests[n], n)):
-        provider = all_tests[nodeid]
-        module = all_modules.get(nodeid, "")
-        short = _short_name(nodeid)
-        row = f"| `{short}` | `{module}` | {provider} |"
-
-        for run in reversed(runs):
-            result = run.get("results", {}).get(nodeid)
-            if result is None:
-                emoji = "N/A"
-            else:
-                status = result.get("status", "N/A") if isinstance(result, dict) else result
-                emoji = STATUS_EMOJI.get(status, "❓")
-            row += f" {emoji} |"
-
-        for _ in range(MAX_HISTORY - len(runs)):
-            row += " N/A |"
-
-        lines.append(row)
-
-    lines.append("")
-    lines.append("**Legend:** ✅ Passed · ❌ Failed · ⏭️ Skipped · ⚠️ Expected Failure (xfail) · N/A Not available")
-    lines.append("")
-
-    return "\n".join(lines)
-
-
-# ---------------------------------------------------------------------------
-# CLI entry point
-# ---------------------------------------------------------------------------
-
-
-def main() -> int:
-    if len(sys.argv) != 4:
-        print("Usage: python aggregate.py <reports-dir> <history-file> <output-file>")
-        return 1
-
-    reports_dir = Path(sys.argv[1])
-    history_path = Path(sys.argv[2])
-    output_path = Path(sys.argv[3])
-
-    print("Aggregating test results from JUnit XML...")
-
-    # Load current run's per-provider XML reports
-    print(f"\nLoading reports from {reports_dir}:")
-    current_run = load_current_run(reports_dir)
-    s = current_run.get("summary", {})
-    total = s.get("total", 0)
-    print(
-        f"  Current run: {s.get('passed', 0)} passed, "
-        f"{s.get('failed', 0)} failed, "
-        f"{s.get('skipped', 0)} skipped "
-        f"(total: {total})"
-    )
-
-    # Load history and append current run (skip empty runs to avoid polluting trend)
-    print(f"\nLoading history from {history_path}:")
-    runs = load_history(history_path)
-    if total > 0:
-        runs.append(current_run)
-        runs = runs[-MAX_HISTORY:]
-    else:
-        print("  Skipping history append (no test results in current run)")
-
-    # Save updated history
-    print(f"\nSaving history to {history_path}:")
-    save_history(history_path, runs)
-
-    # Generate trend report
-    print("\nGenerating trend report...")
-    report = generate_trend_report(runs)
-
-    output_path.parent.mkdir(parents=True, exist_ok=True)
-    output_path.write_text(report, encoding="utf-8")
-    print(f"Trend report written to {output_path}")
-
-    # Print the report to stdout for CI visibility
-    print("\n" + "=" * 80)
-    print(report)
-
-    return 0
-
-
-if __name__ == "__main__":
-    sys.exit(main())
@@ -96,7 +96,7 @@ wheels = [

 [[package]]
 name = "agent-framework"
-version = "1.1.1"
+version = "1.1.0"
 source = { virtual = "." }
 dependencies = [
    { name = "agent-framework-core", extra = ["all"], marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -151,7 +151,7 @@ dev = [

 [[package]]
 name = "agent-framework-a2a"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 source = { editable = "packages/a2a" }
 dependencies = [
    { name = "a2a-sdk", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -166,7 +166,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-ag-ui"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 source = { editable = "packages/ag-ui" }
 dependencies = [
    { name = "ag-ui-protocol", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -194,7 +194,7 @@ provides-extras = ["dev"]

 [[package]]
 name = "agent-framework-anthropic"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 source = { editable = "packages/anthropic" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -209,7 +209,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-azure-ai-search"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 source = { editable = "packages/azure-ai-search" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -224,7 +224,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-azure-cosmos"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 source = { editable = "packages/azure-cosmos" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -239,7 +239,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-azurefunctions"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 source = { editable = "packages/azurefunctions" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -261,7 +261,7 @@ dev = []

 [[package]]
 name = "agent-framework-bedrock"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 source = { editable = "packages/bedrock" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -278,7 +278,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-chatkit"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 source = { editable = "packages/chatkit" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -293,7 +293,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-claude"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 source = { editable = "packages/claude" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -308,7 +308,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-copilotstudio"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 source = { editable = "packages/copilotstudio" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -323,7 +323,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-core"
-version = "1.1.1"
+version = "1.1.0"
 source = { editable = "packages/core" }
 dependencies = [
    { name = "opentelemetry-api", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -395,7 +395,7 @@ provides-extras = ["all"]

 [[package]]
 name = "agent-framework-declarative"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 source = { editable = "packages/declarative" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -420,7 +420,7 @@ dev = [{ name = "types-pyyaml", specifier = "==6.0.12.20250915" }]

 [[package]]
 name = "agent-framework-devui"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 source = { editable = "packages/devui" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -458,7 +458,7 @@ provides-extras = ["dev", "all"]

 [[package]]
 name = "agent-framework-durabletask"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 source = { editable = "packages/durabletask" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -485,7 +485,7 @@ dev = [{ name = "types-python-dateutil", specifier = "==2.9.0.20260402" }]

 [[package]]
 name = "agent-framework-foundry"
-version = "1.1.1"
+version = "1.1.0"
 source = { editable = "packages/foundry" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -504,7 +504,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-foundry-hosting"
-version = "1.0.0a260423"
+version = "1.0.0a260421"
 source = { editable = "packages/foundry_hosting" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -523,7 +523,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-foundry-local"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 source = { editable = "packages/foundry_local" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -540,7 +540,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-gemini"
-version = "1.0.0a260423"
+version = "1.0.0a260421"
 source = { editable = "packages/gemini" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -555,7 +555,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-github-copilot"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 source = { editable = "packages/github_copilot" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -570,7 +570,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-hyperlight"
-version = "1.0.0a260423"
+version = "1.0.0a260421"
 source = { editable = "packages/hyperlight" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -589,7 +589,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-lab"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 source = { editable = "packages/lab" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -670,7 +670,7 @@ dev = [

 [[package]]
 name = "agent-framework-mem0"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 source = { editable = "packages/mem0" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -685,7 +685,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-ollama"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 source = { editable = "packages/ollama" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -700,7 +700,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-openai"
-version = "1.1.1"
+version = "1.1.0"
 source = { editable = "packages/openai" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -715,7 +715,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-orchestrations"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 source = { editable = "packages/orchestrations" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -726,7 +726,7 @@ requires-dist = [{ name = "agent-framework-core", editable = "packages/core" }]

 [[package]]
 name = "agent-framework-purview"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 source = { editable = "packages/purview" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -743,7 +743,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-redis"
-version = "1.0.0b260423"
+version = "1.0.0b260421"
 source = { editable = "packages/redis" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
Author	SHA1	Message	Date
SergeyMenshykhandCopilot	547316b523	Add DI wiring verification tests for AddA2AServer Add three tests to A2AServerServiceCollectionExtensionsTests that verify custom keyed services are actually wired through to the A2AServer, not just that the server resolves non-null: - Custom IAgentHandler: verifies the keyed handler is invoked when processing a SendMessageRequest instead of the default A2AAgentHandler. - Custom AgentSessionStore (no handler): verifies the keyed session store's GetSessionAsync is called during request processing when no custom handler is registered. - Default stores end-to-end: verifies the InMemoryAgentSessionStore and InMemoryTaskStore defaults successfully process a request. Uses a new CreateAgentMockForRequests helper that includes SerializeSessionCoreAsync setup needed by InMemoryAgentSessionStore. All tests call A2AServer.SendMessageAsync directly (no HTTP layer needed) and use CancellationToken timeouts to guard against hangs. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>	2026-04-22 16:25:16 +01:00
SergeyMenshykh	424d66ad74	fix formatting issues	2026-04-22 13:44:22 +01:00
SergeyMenshykh	cd1f4c2a93	address automated code review and formatting issues	2026-04-22 13:31:14 +01:00
SergeyMenshykh	8d208f3bb3	address copilot initial feedback	2026-04-22 12:51:51 +01:00
SergeyMenshykh	373482427c	restore AsyncEnumerable package version	2026-04-22 11:44:54 +01:00
SergeyMenshykhandGitHub	c84203a4a8	Merge branch 'main' into a2a-agent-migration	2026-04-22 11:27:12 +01:00
SergeyMenshykhandCopilot	8f878dcd58	Remove unnecessary using directive in AgentWebChat.AgentHost Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>	2026-04-22 11:20:15 +01:00
SergeyMenshykh GitHub Copilot	c54483f81e	.NET: Split A2A endpoint mapping into protocol-specific methods (#5413 ) * .NET: Refactor A2A hosting registration into A2AServerServiceCollectionExtensions - Rename A2AHostingOptions to A2AServerRegistrationOptions - Move server registration logic from A2AEndpointRouteBuilderExtensions and AIAgentExtensions into new A2AServerServiceCollectionExtensions - Remove A2AProtocolBinding and AIAgentExtensions (consolidated) - Update samples and tests to use the new registration API Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * address copilot comments --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>	2026-04-22 10:38:48 +01:00
SergeyMenshykh GitHub Copilot	275363d15e	.NET: Migrate A2A hosting to A2A SDK v1 (#5363 ) * .NET: Migrate A2A hosting to A2A SDK v1 Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * remove unused agent card --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>	2026-04-21 15:31:56 +01:00
SergeyMenshykh GitHub Copilot	7417eeb7e6	.NET: Use IA2AClientFactory to create A2AClient (#5277 ) * Refactor A2A extensions to use IA2AClientFactory and add ProtocolSelection sample - Update A2AAgentCardExtensions to accept IA2AClientFactory instead of A2AClientOptions - Update A2ACardResolverExtensions to accept IA2AClientFactory - Update A2AClientExtensions to accept IA2AClientFactory - Update A2AAgent to use IA2AClientFactory for client creation - Add A2AAgent_ProtocolSelection sample demonstrating protocol selection - Add comprehensive unit tests for all changes - Update README files with new sample reference Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Reorder params: options before loggerFactory in A2A extensions Move A2AClientOptions parameter before ILoggerFactory in AsAIAgent and GetAIAgentAsync extension methods to follow the repo convention of keeping LoggerFactory and CancellationToken as the last parameters. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>	2026-04-15 17:29:36 +01:00
SergeyMenshykh GitHub Copilot	6ad9279f0f	.NET: Fix stream reconnection for A2AAgent (#5275 ) * Add SSE stream reconnection support to A2AAgent Implement automatic reconnection for SSE streams that disconnect mid-task, using the Last-Event-ID header to resume from where the stream left off. Changes: - Add InvokeStreamingWithReconnectAsync method to A2AAgent with configurable max retries and delay between attempts - Add new log messages for reconnection events - Add A2AAgent_StreamReconnection sample demonstrating the feature - Update existing polling sample to use simplified SendMessageAsync API - Add unit tests for stream reconnection logic Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * address comments * Address PR review feedback - Dispose SSE enumerator before GetTaskAsync fallback to release HTTP connection - Wrap StreamWriter in using blocks with leaveOpen:true and explicit UTF-8 encoding - Print update.Text instead of update object in stream reconnection sample Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>	2026-04-15 14:45:11 +01:00
SergeyMenshykh GitHub Copilot	c1bbaeb31d	Move A2A samples from 04-hosting to 02-agents (#5267 ) Move the A2A sample projects (A2AAgent_AsFunctionTools and A2AAgent_PollingForTaskCompletion) from samples/04-hosting/A2A/ to samples/02-agents/A2A/ to better align with the sample directory structure. Update solution file and samples README accordingly. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>	2026-04-15 12:08:21 +01:00
SergeyMenshykhandGitHub	6173e63f0b	update a2a agent to the latest a2a sdk (#5257 )	2026-04-15 11:08:05 +01:00