.Net: fix: add "status" field to Python dynamic session response #9903
Conversation
This file contains 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
Include the "status" field in the response string returned by Python dynamic sessions. This ensures that the LLM has explicit information about whether the execution succeeded or failed, preventing misinterpretation of stderr or other response elements. This helps avoid hallucinated follow-ups or unnecessary retries by providing clear success/failure indicators. Fixes a usability issue where the LLM assumes success despite execution failures.
github-actions
bot
changed the title
malandis
had a problem deploying
to
integration
GitHub Actions
Failure
There was a problem hiding this comment.
@malandis the unit tests are failing with this change, can you take a look.
Updates the unit test to expect the new status field.
|
@markwallace-microsoft absolutely -- done in 349e2d8 ✅ |
dmytrostruk
approved these changes
Dec 11, 2024
|
Thanks @dmytrostruk . @markwallace-microsoft looks good to go. Just need an additional +1 and to get the branch up to date (if that’s needed before merging). |
esttenorio
approved these changes
Dec 12, 2024
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
github-merge-queue bot
pushed a commit
that referenced
this pull request
Dec 12, 2024
### Motivation and Context Addresses issue #9902 for .NET. Include the "status" field in the response string returned by Python dynamic sessions. Fixes a usability issue where the LLM assumes success despite execution failures. ### Description As per #9902, including the `status` property from the response in the plugin result, we ensure that the LLM has explicit information about whether the execution succeeded or failed, preventing misinterpretation of stderr or other response elements. This helps avoid hallucinated follow-ups or unnecessary retries by providing clear success/failure indicators. ### 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 - [x] I didn't break anyone 😄 --------- Co-authored-by: Evan Mattson <[email protected]>
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
Addresses issue #9902 for .NET.
Include the "status" field in the response string returned by Python dynamic sessions. Fixes a usability issue where the LLM assumes success despite execution failures.
Description
As per #9902, including the
statusproperty from the response in the plugin result, we ensure that the LLM has explicit information about whether the execution succeeded or failed, preventing misinterpretation of stderr or other response elements.This helps avoid hallucinated follow-ups or unnecessary retries by providing clear success/failure indicators.
Contribution Checklist