Python: Add on_intermediate_message callback to the Agent abstraction #11321
Conversation
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
github-actions
bot
changed the title
Python Unit Test Overview
|
moonbox3
previously approved these changes
Apr 1, 2025
alliscode
approved these changes
Apr 2, 2025
alliscode
previously approved these changes
Apr 2, 2025
moonbox3
previously approved these changes
Apr 2, 2025
moonbox3
reviewed
Apr 2, 2025
moonbox3
changed the title
alliscode
previously approved these changes
Apr 3, 2025
moonbox3
previously approved these changes
Apr 3, 2025
github-merge-queue
bot
removed this pull request from the merge queue due to failed status checks
github-merge-queue
bot
removed this pull request from the merge queue due to failed status checks
moonbox3
approved these changes
Apr 3, 2025
alliscode
approved these changes
Apr 3, 2025
github-merge-queue
bot
removed this pull request from the merge queue due to failed status checks
glorious-beard
pushed a commit
to glorious-beard/semantic-kernel
that referenced
this pull request
Apr 6, 2025
…microsoft#11321) ### Motivation and Context <!-- Thank you for your contribution to the semantic-kernel repo! Please help reviewers and future users, providing the following information: 1. Why is this change required? 2. What problem does it solve? 3. What scenario does it contribute to? 4. If it fixes an open issue, please link to the issue here. --> Currently, our agents' `invoke` and `invoke_stream` have inconsistent behavior where the responses may contain different contents. For example, the chat completion agent (`invoke`) may return all content types generated by the agent including function call/result contents that are meant to be internal only, while the assistant agent doesn't return those contents. This creates confusion both for users and developers of SK of what an agent should return when working with agents. ### Description <!-- Describe your changes, the overall approach, the underlying design. These notes will help understanding how your code works. Thanks! --> This PR standardizes the behavior of agents by adding an `on_intermediate_message ` parameter to the `invoke` and `invoke_stream` methods in the `Agent` abstraction. This parameter accepts a callback function that will be called whenever a new message is generated by the agent, except the last one that gets returned to the caller. This allows the caller to inspect what the agent did after a response is returned. In addition, this PR also converges on the behavior of the `invoke` and `invoke_stream` methods (respectively) to return the same content types from all agents, making it easier for users to work with agents ### Contribution Checklist <!-- Before submitting this PR, please make sure: --> - [x] The code builds clean without any errors or warnings - [x] The PR follows the [SK Contribution Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md) and the [pre-submission formatting script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts) raises no violations - [x] All unit tests pass, and I have added new tests where possible - [ ] I didn't break anyone 😄
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
Currently, our agents'
invokeandinvoke_streamhave inconsistent behavior where the responses may contain different contents. For example, the chat completion agent (invoke) may return all content types generated by the agent including function call/result contents that are meant to be internal only, while the assistant agent doesn't return those contents. This creates confusion both for users and developers of SK of what an agent should return when working with agents.Description
This PR standardizes the behavior of agents by adding an
on_intermediate_messageparameter to theinvokeandinvoke_streammethods in theAgentabstraction. This parameter accepts a callback function that will be called whenever a new message is generated by the agent, except the last one that gets returned to the caller. This allows the caller to inspect what the agent did after a response is returned. In addition, this PR also converges on the behavior of theinvokeandinvoke_streammethods (respectively) to return the same content types from all agents, making it easier for users to work with agentsContribution Checklist