[WIP] Add FeedbackPlugin for eval service integration#478
Draft
heyitsaamir wants to merge 1 commit intomainfrom
Draft
[WIP] Add FeedbackPlugin for eval service integration#478heyitsaamir wants to merge 1 commit intomainfrom
heyitsaamir wants to merge 1 commit intomainfrom
Conversation
heyitsaamir
force-pushed
the
aamir/feedback-plugin
branch
from
d51056d to
33278d8
Compare
Introduces a FeedbackPlugin that auto-captures AI traces and user feedback, piping them to eval services via an IFeedbackProvider interface. Also fixes AI example imports to use package names instead of relative dist paths. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
heyitsaamir
force-pushed
the
aamir/feedback-plugin
branch
from
33278d8 to
b39752f
Compare
heyitsaamir
changed the title
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
FeedbackPlugin— auto-captures AI traces (input/output) and Teams feedback (👍/👎), piping them to eval services via anIFeedbackProviderinterface. UsesmessageIdas the correlation key between traces and feedback — no caching layer needed.distpath imports (../../../packages/common/dist/logging/logger) with proper package imports (@microsoft/teams.common).How it works
onActivitystores the user's input per conversationonActivitySentdetectsfeedbackLoopEnabledresponses and callsprovider.logTrace()with the input/output pairprovider.logFeedback()with the reactionDevelopers just add the plugin and send messages with
.addFeedback()— no manual feedback handler needed.Test plan
cd packages/apps && npx jest plugins/feedback— 12 tests passcd packages/apps && npx tsc --noEmit— cleancd examples/ai && npx tsc --noEmit— cleanfeedback <query>, verify trace/feedback logging