fix: do not block negated reasoning-disclosure safety rules - #129
Merged
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
A benign system instruction such as
Do not reveal hidden reasoningmatches the hardreveal hidden reasoningextraction regex.detectDistillreturnsdistill_blocked(403) before credential/slot routing, even for an ordinary Claude request.Fix
Skip only regex matches directly preceded by a negative instruction (
do not,don't,never,must not,should not). Continue checking subsequent matches: a positive extraction request after the safety instruction still blocks. Harvest needles and other guard layers are unchanged.Tests
node --test test/unit/distill-detect.test.mjsnpm run test:unitnpx biome check src/lib/core/distill-detect.mjs test/unit/distill-detect.test.mjsgit diff --check