.Net: Preserve agent execution settings in handoff orchestration#13946
Open
tejakusireddy wants to merge 1 commit intomicrosoft:mainfrom
Open
.Net: Preserve agent execution settings in handoff orchestration#13946tejakusireddy wants to merge 1 commit intomicrosoft:mainfrom
tejakusireddy wants to merge 1 commit intomicrosoft:mainfrom
Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
This PR fixes a .NET handoff orchestration bug where invocation options were created with a fresh base PromptExecutionSettings, causing agent-level provider-specific settings (e.g., OpenAI reasoning_effort) to be lost during orchestration.
Changes:
- Update handoff invocation option creation to clone the agent’s existing
PromptExecutionSettingsper serviceId and then apply the required handoffFunctionChoiceBehavior. - Preserve existing agent argument parameters when constructing
KernelArgumentsfor the handoff invocation. - Add a regression unit test verifying
reasoning_effortis present in the outgoing OpenAI request body during handoff orchestration.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
| dotnet/src/Agents/Orchestration/Handoff/HandoffActor.cs | Clones agent execution settings (preserving provider-specific fields) and applies handoff auto function choice behavior without dropping settings. |
| dotnet/src/Agents/UnitTests/Orchestration/HandoffOrchestrationTests.cs | Adds regression coverage to ensure OpenAI reasoning_effort survives orchestration and is serialized into the request body. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Motivation and Context
Fixes #13935.
Handoff orchestration created invocation options with a new base
PromptExecutionSettings, which dropped agent-level provider-specific settings such as OpenAIreasoning_effort.Description
Preserves the agent's existing execution settings when creating handoff invocation options by cloning them before applying handoff function choice behavior.
Also preserves existing agent argument parameters and adds a regression test that verifies
reasoning_effortis included in the outgoing request body.Contribution Checklist