feat: classify_satisfaction — semantic user satisfaction detection v1.11.1#166
Merged
devonakelley merged 1 commit intomainfrom Apr 24, 2026
Merged
feat: classify_satisfaction — semantic user satisfaction detection v1.11.1#166devonakelley merged 1 commit intomainfrom
devonakelley merged 1 commit intomainfrom
Conversation
….11.1
Adds classify_satisfaction(user_message, prior_output) -> 'negative'|'positive'|'neutral'
Uses a cheap LLM (DeepSeek → GPT-4o-mini → Claude Haiku) to semantically interpret
whether the user's follow-up message indicates satisfaction with the prior output.
No keyword matching. Fails open (returns 'neutral') when no provider key available.
Also adds classify_satisfaction_async() for fire-and-forget usage in agent loops.
Exported from kalibr top-level: from kalibr import classify_satisfaction
Usage:
result = classify_satisfaction(user_message, prior_output)
if result == 'negative':
user_rejected()
elif result == 'positive':
user_accepted()
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds semantic satisfaction classification — no keyword matching.
Uses a cheap LLM (DeepSeek first, then GPT-4o-mini, then Claude Haiku) to semantically interpret user intent. Fails open to 'neutral' when no provider key available — never blocks.