Feedback-Loop buttons and Generated-by-AI label not showing when ending a streaming

Open
#587 0 comments 0 reactions 1 assignee View on GitHub

@ceciliaavila is already working on this.

Since Sep 17, 2026.

Assessment

This issue has not been assessed yet.

Description

Description

The feedback buttons and AI-Generated label are not shown in a streaming message even when context.streaming_response.set_feedback_loop(True) and context.streaming_response.set_generated_by_ai_label(True) are set.

Image

There are two bugs causing this issue:

  1. Feedback metadata remains contradictory

In StreamingResponse._send_activity(), setting both the feedback loop and its type enters this branch:

if self._enable_feedback_loop and self._feedback_loop_type:
    streaminfo_entity.feedback_loop = {"type": self._feedback_loop_type}
else:
    streaminfo_entity.feedback_loop_enabled = self._enable_feedback_loop

Because the else is skipped, feedback_loop_enabled retains the StreamInfo default of False, producing:

{
  "feedbackLoop": {
    "type": "default"
  },
  "feedbackLoopEnabled": false
}
  1. AI metadata requires citations

Activity.add_ai_metadata() currently wraps the entire operation in:

if citations:

Consequently, it never adds an AIEntity when the message has no citations—even when set_generated_by_ai_label(True) and a sensitivity label are configured.

Dominant language
Python
Stars
211
Forks
90
Avg merge
1d 9h
Merged PRs (30d)
20

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from microsoft/Agents-for-python

All issues in microsoft/Agents-for-python

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.