Merge and move scripts (#4308)

* .NET: Add Microsoft Fabric sample #3674 (#4230) Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * Python: Phase 2: Embedding clients for Ollama, Bedrock, and Azure AI Inference (#4207) * Phase 2: Embedding clients for Ollama, Bedrock, and Azure AI Inference Add embedding client implementations to existing provider packages: - OllamaEmbeddingClient: Text embeddings via Ollama's embed API - BedrockEmbeddingClient: Text embeddings via Amazon Titan on Bedrock - AzureAIInferenceEmbeddingClient: Text and image embeddings via Azure AI Inference, supporting Content | str input with separate model IDs for text (AZURE_AI_INFERENCE_EMBEDDING_MODEL_ID) and image (AZURE_AI_INFERENCE_IMAGE_EMBEDDING_MODEL_ID) endpoints Additional changes: - Rename EmbeddingCoT -> EmbeddingT, EmbeddingOptionsCoT -> EmbeddingOptionsT - Add otel_provider_name passthrough to all embedding clients - Register integration pytest marker in all packages - Add lazy-loading namespace exports for Ollama and Bedrock embeddings - Add image embedding sample using Cohere-embed-v3-english - Add azure-ai-inference dependency to azure-ai package Part of #1188 Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Fix mypy duplicate name and ruff lint issues - Rename second 'vector' variable to 'img_vector' in image embedding loop - Combine nested with statements in tests - Remove unused result assignments in tests Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * updates from feedback * Fix CI failures in embedding usage handling - Fix Azure AI embedding mypy issues by normalizing vectors to list[float], safely accumulating optional usage token fields, and filtering None entries before constructing GeneratedEmbeddings - Avoid Bandit false positive by initializing usage details as an empty dict - Update OpenAI embedding tests to assert canonical usage keys (input_token_count/total_token_count) Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * [Purview] Mark responses as responses and fix epoch bug for python long overflow (#4225) * .NET: Support InvokeMcpTool for declarative workflows (#4204) * Initial implementation of InvokeMcpTool in declarative workflow * Cleaned up sample implementation * Updated sample comments. * Added missing executor routing attribute * Fix PR comments. * Updated based on PR comments. * Updated based on PR comments. * Removed unnecessary using statement. * Update Python package versions to rc2 (#4258) - Bump core and azure-ai to 1.0.0rc2 - Bump preview packages to 1.0.0b260225 - Update dependencies to >=1.0.0rc2 - Add CHANGELOG entries for changes since rc1 - Update uv.lock Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * .NET: Fixing issue where OpenTelemetry span is never exported in .NET in-process workflow execution (#4196) * 1. Add reproduction test for issue #4155: workflow.run Activity never stopped in streaming OffThread path The WorkflowRunActivity_IsStopped_Streaming_OffThread test demonstrates that the workflow.run OpenTelemetry Activity created in StreamingRunEventStream.RunLoopAsync is started but never stopped when using the OffThread/Default streaming execution. The background run loop keeps running after event consumption completes, so the using Activity? declaration never disposes until explicit StopAsync() is called. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> 2. Fix workflow.run Activity never stopped in streaming OffThread execution (#4155) The workflow.run OpenTelemetry Activity in StreamingRunEventStream.RunLoopAsync was scoped to the method lifetime via 'using'. Since the run loop only exits on cancellation, the Activity was never stopped/exported until explicit disposal. Fix: Remove 'using' and explicitly dispose the Activity when the workflow reaches Idle status (all supersteps complete). A safety-net disposal in the finally block handles cancellation and error paths. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Add root-level workflow.session activity spanning run loop lifetime\n\nImplements two-level telemetry hierarchy per PR feedback from lokitoth:\n- workflow.session: spans the entire run loop / stream lifetime\n- workflow_invoke: per input-to-halt cycle, nested within the session\n\nThis ensures the session activity stays open across multiple turns,\nwhile individual run activities are created and disposed per cycle.\n\nAlso fixes linkedSource CancellationTokenSource disposal leak in\nStreamingRunEventStream (added using declaration)." * Address Copilot review: fix Activity/CTS disposal, rename activity, add error tag\n\n1. LockstepRunEventStream: Remove 'using' from Activity in async iterator\n and manually dispose in finally block (fixes #4155 pattern). Also dispose\n linkedSource CTS in finally to prevent leak.\n2. Tags.cs: Add ErrorMessage (\"error.message\") tag for runtime errors,\n distinct from BuildErrorMessage (\"build.error.message\").\n3. ActivityNames: Rename WorkflowRun from \"workflow_invoke\" to \"workflow.run\"\n for cross-language consistency.\n4. WorkflowTelemetryContext: Fix XML doc to say \"outer/parent span\" instead\n of \"root-level span\".\n5. ObservabilityTests: Assert WorkflowSession absence when DisableWorkflowRun\n is true.\n6. WorkflowRunActivityStopTests: Fix streaming test race by disposing\n StreamingRun before asserting activities are stopped.\n7. StreamingRunEventStream/LockstepRunEventStream: Use Tags.ErrorMessage\n instead of Tags.BuildErrorMessage for runtime error events." * Review fixes: revert workflow_invoke rename, use 'using' for linkedSource, move SessionStarted earlier\n\n- Revert ActivityNames.WorkflowRun back to \"workflow_invoke\" (OTEL semantic convention contract)\n- Use 'using' declaration for linkedSource CTS in LockstepRunEventStream (no timing sensitivity)\n- Move SessionStarted event before WaitForInputAsync in StreamingRunEventStream to match Lockstep behavior" * Improve naming and comments in WorkflowRunActivityStopTests" * Prevent session Activity.Current leak in lockstep mode, add nesting test Save and restore Activity.Current in LockstepRunEventStream.Start() so the session activity doesn't leak into caller code via AsyncLocal. Re-establish Activity.Current = sessionActivity before creating the run activity in TakeEventStreamAsync to preserve parent-child nesting. Add test verifying app activities after RunAsync are not parented under the session, and that the workflow_invoke activity nests under the session." * Fix stale XML doc: WorkflowRun -> WorkflowInvoke in ObservabilityTests --------- Co-authored-by: alliscode <bentho@microsoft.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Python / .NET Samples - Restructure and Improve Samples (Feature Branc… (#4092) * Python: .NET Samples - Restructure and Improve Samples (Feature Branch) (#4091) * Moved by agent (#4094) * Fix readme links * .NET Samples - Create `04-hosting` learning path step (#4098) * Agent move * Agent reorderd * Remove A2A section from README Removed A2A section from the Getting Started README. * Agent fixed links * Fix broken sample links in durable-agents README (#4101) * Initial plan * Fix broken internal links in documentation Co-authored-by: crickman <66376200+crickman@users.noreply.github.com> * Revert template link changes; keep only durable-agents README fix Co-authored-by: crickman <66376200+crickman@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: crickman <66376200+crickman@users.noreply.github.com> * .NET Samples - Create `03-workflows` learning path step (#4102) * Fix solution project path * Python: Fix broken markdown links to repo resources (outside /docs) (#4105) * Initial plan * Fix broken markdown links to repo resources Co-authored-by: crickman <66376200+crickman@users.noreply.github.com> * Update README to rename .NET Workflows Samples section --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: crickman <66376200+crickman@users.noreply.github.com> * .NET Samples - Create `02-agents` learning path step (#4107) * .NET: Fix broken relative link in GroupChatToolApproval README (#4108) * Initial plan * Fix broken link in GroupChatToolApproval README Co-authored-by: crickman <66376200+crickman@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: crickman <66376200+crickman@users.noreply.github.com> * Update labeler configuration for workflow samples * .NET - Reorder Agents samples to start from Step01 instead of Step04 (#4110) * Fix solution * Resolve new sample paths * Move new AgentSkills and AgentWithMemory_Step04 samples * Fix link * Fix readme path * fix: update stale dotnet/samples/Durable path reference in AGENTS.md Co-authored-by: crickman <66376200+crickman@users.noreply.github.com> * Moved new sample * Update solution * Resolve merge (new sample) * Sync to new sample - FoundryAgents_Step21_BingCustomSearch * Updated README * .NET Samples - Configuration Naming Update (#4149) * .NET: Restore AzureFunctions index parity with ConsoleApps under DurableAgents samples (#4221) * Clean-up `05_host_your_agent` * Config setting consistency * Refine samples * AGENTS.md * Move new samples * Re-order samples * Move new project and fixup solution * Fixup model config * Fix up new UT project --------- Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> * Python: Fix Bedrock embedding test stub missing meta attribute (#4287) * Fix Bedrock embedding test stub missing meta attribute * Increase test coverage so gate passes * Python: (ag-ui): fix approval payloads being re-processed on subsequent conversation turns (#4232) * Fix ag-ui tool call issue * Safe json fix * Python: Update workflow orchestration samples to use AzureOpenAIResponsesClient (#4285) * Update workflow orchestration samples to use AzureOpenAIResponsesClient * Fix broken link * Move scripts to scripts folder --------- Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Co-authored-by: Rishabh Chawla <rishabhchawla1995@gmail.com> Co-authored-by: Peter Ibekwe <109177538+peibekwe@users.noreply.github.com> Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com> Co-authored-by: Ben Thomas <ben.thomas@microsoft.com> Co-authored-by: alliscode <bentho@microsoft.com> Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com>
2026-06-16 21:04:09 +08:00 · 2026-02-26 10:49:07 +00:00
parent cc1ef730e3
commit 8b191de936
871 changed files with 7688 additions and 1696 deletions
@@ -56,6 +56,7 @@ from ._utils import (
    get_conversation_id_from_update,
    get_role_value,
    make_json_safe,
+    normalize_agui_role,
 )

 if TYPE_CHECKING:
@@ -450,7 +451,7 @@ async def _resolve_approval_responses(
    _convert_approval_results_to_tool_messages(messages)


-def _convert_approval_results_to_tool_messages(messages: list[Any]) -> None:
+def _convert_approval_results_to_tool_messages(messages: list[Message]) -> None:
    """Convert function_result content in user messages to proper tool messages.

    After approval processing, tool results end up in user messages. OpenAI and other
@@ -462,14 +463,14 @@ def _convert_approval_results_to_tool_messages(messages: list[Any]) -> None:
    Args:
        messages: List of Message objects to process
    """
-    result: list[Any] = []
+    result: list[Message] = []

    for msg in messages:
        if get_role_value(msg) != "user":
            result.append(msg)
            continue

-        msg_contents = cast(list[Content], getattr(msg, "contents", None) or [])
+        msg_contents = msg.contents or []
        function_results: list[Content] = [content for content in msg_contents if content.type == "function_result"]
        other_contents: list[Content] = [content for content in msg_contents if content.type != "function_result"]

@@ -492,6 +493,68 @@ def _convert_approval_results_to_tool_messages(messages: list[Any]) -> None:
    messages[:] = result


+def _clean_resolved_approvals_from_snapshot(
+    snapshot_messages: list[dict[str, Any]],
+    resolved_messages: list[Message],
+) -> None:
+    """Replace approval payloads in snapshot messages with actual tool results.
+
+    After _resolve_approval_responses executes approved tools, the snapshot still
+    contains the raw approval payload (e.g. ``{"accepted": true}``). When this
+    snapshot is sent back to CopilotKit via ``MessagesSnapshotEvent``, the approval
+    payload persists in the conversation history.  On the next turn CopilotKit
+    re-sends the full history and the adapter re-detects the approval, causing the
+    tool to be re-executed.
+
+    This function replaces approval tool-message content in ``snapshot_messages``
+    with the real tool result so the approval payload no longer appears in the
+    history sent to the client.
+
+    Args:
+        snapshot_messages: Raw AG-UI snapshot messages (mutated in place).
+        resolved_messages: Provider messages after approval resolution.
+    """
+    # Build call_id → result text from resolved tool messages
+    result_by_call_id: dict[str, str] = {}
+    for msg in resolved_messages:
+        if get_role_value(msg) != "tool":
+            continue
+        for content in msg.contents or []:
+            if content.type == "function_result" and content.call_id:
+                result_text = (
+                    content.result if isinstance(content.result, str) else json.dumps(make_json_safe(content.result))
+                )
+                result_by_call_id[str(content.call_id)] = result_text
+
+    if not result_by_call_id:
+        return
+
+    for snap_msg in snapshot_messages:
+        if normalize_agui_role(snap_msg.get("role", "")) != "tool":
+            continue
+        raw_content = snap_msg.get("content")
+        if not isinstance(raw_content, str):
+            continue
+
+        # Check if this is an approval payload
+        try:
+            parsed = json.loads(raw_content)
+        except (json.JSONDecodeError, TypeError):
+            continue
+        if not isinstance(parsed, dict) or "accepted" not in parsed:
+            continue
+
+        # Find matching tool result by toolCallId
+        tool_call_id = snap_msg.get("toolCallId") or snap_msg.get("tool_call_id") or ""
+        replacement = result_by_call_id.get(str(tool_call_id))
+        if replacement is not None:
+            snap_msg["content"] = replacement
+            logger.info(
+                "Replaced approval payload in snapshot for tool_call_id=%s with actual result",
+                tool_call_id,
+            )
+
+
 def _build_messages_snapshot(
    flow: FlowState,
    snapshot_messages: list[dict[str, Any]],
@@ -646,6 +709,10 @@ async def run_agent_stream(
    tools_for_execution = tools if tools is not None else server_tools
    await _resolve_approval_responses(messages, tools_for_execution, agent, run_kwargs)

+    # Defense-in-depth: replace approval payloads in snapshot with actual tool results
+    # so CopilotKit does not re-send stale approval content on subsequent turns.
+    _clean_resolved_approvals_from_snapshot(snapshot_messages, messages)
+
    # Feature #3: Emit StateSnapshotEvent for approved state-changing tools before agent runs
    approved_state_updates = _extract_approved_state_updates(messages, predictive_handler)
    approved_state_snapshot_emitted = False
@@ -331,10 +331,6 @@ wrapped_agent = AgentFrameworkAgent(
    orchestrators=[MyCustomOrchestrator(), DefaultOrchestrator()],
 )

-## Documentation
-
-For detailed documentation, see [DESIGN.md](DESIGN.md).
-
 ## License

 MIT
@@ -1,6 +1,6 @@
 [project]
 name = "agent-framework-ag-ui"
-version = "1.0.0b260219"
+version = "1.0.0b260225"
 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>=1.0.0rc1",
+    "agent-framework-core>=1.0.0rc2",
    "ag-ui-protocol>=0.1.9",
    "fastapi>=0.115.0",
    "uvicorn>=0.30.0"
@@ -45,6 +45,9 @@ packages = ["agent_framework_ag_ui", "agent_framework_ag_ui_examples"]
 asyncio_mode = "auto"
 testpaths = ["tests/ag_ui"]
 pythonpath = ["."]
+markers = [
+    "integration: marks tests as integration tests that require external services",
+]

 [tool.ruff]
 line-length = 120
@@ -866,3 +866,45 @@ def test_agui_messages_to_snapshot_format_basic():
    assert result[0]["content"] == "Hello"
    assert result[1]["role"] == "assistant"
    assert result[1]["content"] == "Hi there"
+
+
+def test_agui_fresh_approval_is_still_processed():
+    """A fresh approval (no assistant response after it) must still produce function_approval_response.
+
+    On Turn 2, the approval is fresh (no subsequent assistant message), so it
+    must be processed normally to execute the tool.
+    """
+    messages_input = [
+        # Turn 1: user asks something
+        {"role": "user", "content": "What time is it?", "id": "msg_1"},
+        # Turn 1: assistant calls a tool
+        {
+            "role": "assistant",
+            "content": "",
+            "tool_calls": [
+                {
+                    "id": "call_456",
+                    "type": "function",
+                    "function": {"name": "get_datetime", "arguments": "{}"},
+                }
+            ],
+            "id": "msg_2",
+        },
+        # Turn 2: user approves (no assistant message after this)
+        {
+            "role": "tool",
+            "content": json.dumps({"accepted": True}),
+            "toolCallId": "call_456",
+            "id": "msg_3",
+        },
+    ]
+
+    messages = agui_messages_to_agent_framework(messages_input)
+
+    # The fresh approval SHOULD produce a function_approval_response
+    approval_contents = [
+        content for msg in messages for content in (msg.contents or []) if content.type == "function_approval_response"
+    ]
+    assert len(approval_contents) == 1, "Fresh approval should produce function_approval_response"
+    assert approval_contents[0].approved is True
+    assert approval_contents[0].function_call.name == "get_datetime"
@@ -262,3 +262,141 @@ def test_sanitize_tool_history_filters_confirm_changes_from_assistant_messages()
    # (the approval response is handled separately by the framework)
    tool_call_ids = {str(msg.contents[0].call_id) for msg in tool_messages}
    assert "call_c1" not in tool_call_ids  # No synthetic result for confirm_changes
+
+
+# ---------------------------------------------------------------------------
+# Tests for _clean_resolved_approvals_from_snapshot
+# ---------------------------------------------------------------------------
+
+
+def test_clean_resolved_approvals_from_snapshot() -> None:
+    """Approval payload in snapshot should be replaced with the actual tool result."""
+    import json
+
+    from agent_framework_ag_ui._agent_run import _clean_resolved_approvals_from_snapshot
+
+    # Snapshot still has the approval payload
+    snapshot_messages = [
+        {"role": "user", "content": "What time is it?", "id": "msg_1"},
+        {
+            "role": "assistant",
+            "content": "",
+            "tool_calls": [
+                {"id": "call_123", "type": "function", "function": {"name": "get_datetime", "arguments": "{}"}}
+            ],
+            "id": "msg_2",
+        },
+        {
+            "role": "tool",
+            "content": json.dumps({"accepted": True}),
+            "toolCallId": "call_123",
+            "id": "msg_3",
+        },
+    ]
+
+    # Resolved provider messages have the actual tool result
+    resolved_messages = [
+        Message(role="user", contents=[Content.from_text(text="What time is it?")]),
+        Message(
+            role="assistant",
+            contents=[Content.from_function_call(call_id="call_123", name="get_datetime", arguments="{}")],
+        ),
+        Message(
+            role="tool",
+            contents=[Content.from_function_result(call_id="call_123", result="2024-01-01 12:00:00")],
+        ),
+    ]
+
+    _clean_resolved_approvals_from_snapshot(snapshot_messages, resolved_messages)
+
+    # The approval payload should now be replaced with the tool result
+    tool_snap = snapshot_messages[2]
+    assert tool_snap["content"] == "2024-01-01 12:00:00"
+
+
+def test_clean_resolved_approvals_from_snapshot_no_approvals() -> None:
+    """When there are no approval payloads, snapshot should be unchanged."""
+    from agent_framework_ag_ui._agent_run import _clean_resolved_approvals_from_snapshot  # type: ignore
+
+    snapshot_messages = [
+        {"role": "user", "content": "Hello", "id": "msg_1"},
+        {"role": "assistant", "content": "Hi there", "id": "msg_2"},
+    ]
+    original = [dict(m) for m in snapshot_messages]
+
+    resolved_messages = [
+        Message(role="user", contents=[Content.from_text(text="Hello")]),
+        Message(role="assistant", contents=[Content.from_text(text="Hi there")]),
+    ]
+
+    _clean_resolved_approvals_from_snapshot(snapshot_messages, resolved_messages)
+
+    # Nothing should have changed
+    assert snapshot_messages == original
+
+
+def test_cleaned_snapshot_prevents_approval_reprocessing() -> None:
+    """After snapshot cleaning, approval payload is replaced so it won't re-trigger on next turn.
+
+    Simulates what happens on Turn 2: the approval is processed, the tool executes,
+    and _clean_resolved_approvals_from_snapshot replaces the approval payload with the
+    real tool result. On Turn 3, CopilotKit re-sends the cleaned snapshot, which no
+    longer contains an approval payload — so no function_approval_response is produced.
+    """
+    import json
+
+    from agent_framework_ag_ui._agent_run import _clean_resolved_approvals_from_snapshot
+    from agent_framework_ag_ui._message_adapters import normalize_agui_input_messages
+
+    # Turn 2 snapshot: still has the raw approval payload
+    snapshot_messages = [
+        {"role": "user", "content": "What time is it?", "id": "msg_1"},
+        {
+            "role": "assistant",
+            "content": "",
+            "tool_calls": [
+                {"id": "call_789", "type": "function", "function": {"name": "get_datetime", "arguments": "{}"}}
+            ],
+            "id": "msg_2",
+        },
+        {
+            "role": "tool",
+            "content": json.dumps({"accepted": True}),
+            "toolCallId": "call_789",
+            "id": "msg_3",
+        },
+    ]
+
+    # Resolved provider messages after tool execution
+    resolved_messages = [
+        Message(role="user", contents=[Content.from_text(text="What time is it?")]),
+        Message(
+            role="assistant",
+            contents=[Content.from_function_call(call_id="call_789", name="get_datetime", arguments="{}")],
+        ),
+        Message(
+            role="tool",
+            contents=[Content.from_function_result(call_id="call_789", result="2024-01-01 12:00:00")],
+        ),
+    ]
+
+    # Fix B: clean the snapshot
+    _clean_resolved_approvals_from_snapshot(snapshot_messages, resolved_messages)
+
+    # Snapshot should now have the real tool result
+    assert snapshot_messages[2]["content"] == "2024-01-01 12:00:00"
+
+    # Simulate Turn 3: CopilotKit re-sends the cleaned snapshot + new messages
+    turn3_messages = list(snapshot_messages) + [
+        {"role": "assistant", "content": "It is 12:00 PM.", "id": "msg_4"},
+        {"role": "user", "content": "Thanks!", "id": "msg_5"},
+    ]
+
+    provider_messages, _ = normalize_agui_input_messages(turn3_messages)
+
+    # No function_approval_response should exist — the approval payload is gone
+    for msg in provider_messages:
+        for content in msg.contents or []:
+            assert content.type != "function_approval_response", (
+                f"Stale approval was re-processed on subsequent turn: {content}"
+            )