Fix synthetic user extending conversations with unrelated questions#47
Merged
Merged
Conversation
2c7a564 to
e693a32
Compare
…mpletion Two issues causing conversations to run too long: 1. Synthetic user inventing new questions after being satisfied - Added explicit instructions to ONLY ask about ORIGINAL question - Added "END when satisfied" instructions - Added "NEVER invent follow-up questions" instructions 2. check_criteria judge not recognizing user satisfaction - User satisfaction is now the PRIMARY signal for completion - If user says "thanks", "that's what I needed", etc. → ALL CRITERIA MET - Changed from evaluating technical criteria to detecting conversation completion - Do NOT continue nitpicking criteria if user has expressed satisfaction Fixes #46
e693a32 to
5087f18
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Two issues causing conversations to run too long:
1. Synthetic user inventing new questions
After being satisfied, the synthetic user was asking completely unrelated follow-up questions.
Fix: Added explicit instructions:
2. check_criteria judge not recognizing user satisfaction
The judge was nitpicking individual criteria even after the user expressed satisfaction, causing infinite "thanks" loops.
Fix: Made user satisfaction the PRIMARY signal:
Test Plan
Fixes #46