* fix: strip function_call and text_reasoning from cross-agent workflow handoff
When a reasoning model (e.g. gpt-5-mini) runs as Agent 1 in a workflow, its
response includes text_reasoning items (with server-scoped IDs like rs_XXXX)
and function_call items. Forwarding these to Agent 2 in a fresh conversation
caused API errors because the reasoning/call IDs are scoped to the original
stored response context.
Changes:
- Strip 'function_call', 'text_reasoning', 'function_approval_request', and
'function_approval_response' from handoff messages in _agent_executor.py
- Keep 'function_result' so the actual tool output content is preserved for
the next agent's context
- Update unit tests to reflect that function_result messages survive handoff
(messages grow from 2→3: user, tool(result), assistant(summary))
- Fix incorrect test assertions in test_function_invocation_stop_clears_*
that assumed the client layer updates session.service_session_id
- Also fixed _extract_function_calls to search all messages with call_id
deduplication, and the error-limit stop path to submit function_call_output
items before halting (via tool_choice=none cleanup call)
Relates to: https://github.com/microsoft/agent-framework/issues/4047
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix: reasoning model workflow handoff and history serialization
Fixes multiple related issues when using reasoning models (gpt-5-mini,
gpt-5.2) in multi-agent workflows that chain agents via from_response
or replay full conversation history via AgentExecutorRequest.
## Reasoning items always emitted on output_item.added
When a reasoning model produces encrypted or hidden reasoning (no
visible text), the Responses API still fires a reasoning output item
without any reasoning_text.delta events. Previously no text_reasoning
Content was emitted in that case, making it invisible to downstream
logic. Both the non-streaming (_parse_response_from_openai) and
streaming (output_item.added) paths now always emit at least one
text_reasoning Content — with empty text if no content is available —
so co-occurrence detection and serialization guards work reliably.
## Reasoning items only serialized when paired with a function_call
The Responses API only accepts reasoning items in input when they
directly preceded a function_call in the original response. Sending a
reasoning item that preceded a text response (no tool call) causes:
"reasoning was provided without its required following item"
_prepare_message_for_openai now checks has_function_call per message
and skips text_reasoning serialization when there is no accompanying
function_call.
## summary field is an array, not an object
The reasoning item summary field sent to the Responses API must be an
array of objects ([{"type": "summary_text", "text": ...}]), not a
single object. Fixed _prepare_content_for_openai accordingly.
## service_session_id cleared when explicit history is provided
When a workflow coordinator replays a full conversation (including
function calls from a previous agent run) back to an executor via
AgentExecutorRequest or from_response, the executor's session still
held a service_session_id (previous_response_id) from the prior run.
The API then received the same function-call items twice — once from
previous_response_id (server-stored) and once from the explicit input —
causing: "Duplicate item found with id fc_...".
AgentExecutor.run (when should_respond=True) and from_response now
reset self._session.service_session_id = None before running so that
explicit input is the sole source of conversation context.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* small improvements in text reasoning
* refactor: add reset_service_session to AgentExecutorRequest for explicit history replay
Replace the implicit 'always clear service_session_id when should_respond=True'
with an explicit opt-in field on AgentExecutorRequest.
The old approach used should_respond=True as a proxy for 'full history replay',
but that conflates two distinct intents:
- Orchestrations group chat sends should_respond=True with an empty/single-message
list (not a full replay) — unnecessarily clearing service_session_id.
- HITL / feedback coordinators send the full prior conversation and truly need
a fresh service session ID to avoid duplicate-item API errors.
Changes:
- Add AgentExecutorRequest.reset_service_session: bool = False
- AgentExecutor.run only clears service_session_id when this flag is True
- AgentExecutor.from_response unchanged (always clears; always full conversation)
- Set reset_service_session=True in all full-history-replay call sites:
agents_with_HITL.py, azure_chat_agents_tool_calls_with_feedback.py,
autogen-migration round-robin coordinator, tau2 runner
- Update _FullHistoryReplayCoordinator test helper to pass the flag
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* comment update
* fixes from feedback
* fix test
* reverted changes to agent executor
* fix: remove reset_service_session from tau2 runner
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* two other reverts
* fix sample
---------
Co-authored-by: Giles Odigwe <79032838+giles17@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Eduard van Valkenburg
·
2026-02-19 21:02:20 +00:00
* Fix handoff orchestration not passing user message to handoff target agent (#3161)
Filter out internal handoff function call and tool result messages before
passing conversation history to the target agent's LLM. These messages
confused the model into ignoring the original user question.
* Add handoff tool call filtering behavior and enhance workflow builder
- Introduced HandoffToolCallFilteringBehavior enum to specify filtering behavior for tool call contents in handoff workflows.
- Updated HandoffsWorkflowBuilder to support customizable handoff instructions and tool call filtering behavior.
- Enhanced HandoffAgentExecutor to utilize new filtering options for improved message handling during agent handoffs.
* Enhance handoff message filtering logic and add unit tests for filtering behaviors
* Refactor HandoffMessagesFilter to remove unused handoff function names and enhance filtering logic for non-handoff function calls
* Refactor HandoffMessagesFilter to streamline FilterCandidateState initialization and improve clarity
* Refactor HandoffMessagesFilter to improve filtering logic and add integration tests for handoff workflows
* fix: HandoffAgentExecutor tests
* [BREAKING] refactor: Decouple Checkpointing and Execution APIs
With this change, Checkpointing becomes an property of an IWorkflowExecutionEnvironment. This lets environments that are tightly-coupled to their CheckpointManager avoid needing to present APIs that would not work (e.g. taking in an InMemory CheckpointManager for Durable Tasks, for example)
* refactor: Normalize IsCheckpointingEnabled naming
- Rename UserNameProvider → UserMemoryProvider
- Use session state (state dict) instead of instance variables
- Use context.extend_instructions() instead of context.instructions.append()
- Use DEFAULT_SOURCE_ID class attribute
- Fix imports to use public agent_framework API
- Add session state inspection at end of sample
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Eduard van Valkenburg
·
2026-02-19 15:34:49 +00:00
Track the last CheckpointInfo in InProcessRunner so that newly created
checkpoints reference their parent. When resuming from a checkpoint,
the resumed-from checkpoint becomes the parent of the next checkpoint.
Adds tests verifying:
- First checkpoint has null parent
- Subsequent checkpoints chain parents correctly
- Checkpoint after resume references the resumed-from checkpoint
* feat: Implement Polymorphic Routing
* feat: Add support for Send/Yield annotations with basic Executor
* Adds annotations to Declarative workflow executors
* fix: Address PR Comments
* Implicit filter in collection loops
* Remove debug / usused / superfluous code
* Fix ProtocolBuilder implicit output registrations
* Fix logic error in ExecuteRouteGeneratorTests.ClassWithManualConfigureProtocol_DoesNotGenerate
* fix: Solidify type checks and send/yield type registrations
* fix: Suppress generation of TurnTokens out of AggregateTurnMessagesExecutor
* Fixes an issue where ConcurrentEndExecutor is not expecting TurnTokens.
* fix: Add ProtocolBuilder support for chained-delegation
* Updates Declarative pacakge to rely on chained-delegation Send/Yield registration
* Renames DeclarativeActionExectuor's new ExecuteAsync to ExecuteActionAsync to avoid colliding with Executor.ExecutoeAsync
* fix: Address PR Comments
* Fixes type mapping in FanInEdgeRunner
* Fixes and expalins send/yield type registration in FunctionExecutor
* fixup: build-break
* fix: Add missing SendsMesage declaration to InvokeAzureAgentExecutor
* Fix FoundryAgents_Step15_ComputerUse sample for Azure Agents API
The Azure Agents API rejects previous_response_id alongside computer_call_output
items, unlike the vanilla OpenAI Responses API. This fix:
- Send all prior response output items (reasoning, computer_call, etc.) as input
items in follow-up calls so the API has full conversation context
- Create a fresh session per call to avoid ConversationId/previous_response_id
- Use currentCallId instead of initialCallId for computer_call_output
- Clear ContinuationToken after polling to prevent stale tokens
- Remove unused initialCallId tracking variable
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Address comments
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Initial Implementation of InvokeFunctionTool
* Added unit test for InvokeFunctionTool executor.
* Implemented unit and integration tests for InvokeFunctionTool.
* Add sample for InvokeFunctionTool in declarative workflows.
* Remove unused sample and updated comments.
* Updating to official OM release with InvokeFunctionTool
* Fix formatting issues.
* Updated PowerFx version
* Update test fixture
* Cleanup - Removed unused method in InvokeFunctionToolExecutor
* Update test based on PR feedback.
* Update based on PR comments
Copilot ·
Chris ·
Tao Chen ·
Chris Rickman ·
Eduard van Valkenburg ·
Jacob Alber ·
westey ·
Dmytro Struk ·
Roger Barreto ·
dependabot[bot] ·
Giles Odigwe ·
Peter Ibekwe ·