fix: gate debug recommendation filter log behind shouldInject - #279
Open
ranxianglei wants to merge 1 commit into
Open
fix: gate debug recommendation filter log behind shouldInject#279ranxianglei wants to merge 1 commit into
ranxianglei wants to merge 1 commit into
Conversation
… per-turn log noise
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
When
config.debug: true, the recommendation filterlogger.debugfired on EVERY message transform hook call — even when no nudge was being injected. In normal sessions with compressible ranges (almost always), this produced a log entry per message. The user saw constant[ACP Debug] Recommendation filter:entries and toast notifications even when there was nothing to compress.Fix
Moved the recommendation filter
logger.debugfrom its per-turn position (beforeshouldInjectdecision) to inside theshouldInjectblock. Now only fires when a nudge is actually being injected — i.e., when there is real compression to recommend.Verification