fix(tools): exempt invoke_skill and load_skill from utility gate#3165
Merged
fix(tools): exempt invoke_skill and load_skill from utility gate#3165
Conversation
UtilityScoringConfig::default() populated exempt_tools with an empty Vec, so the utility scorer blocked invoke_skill calls even though AdversarialPolicyConfig and vigil already exempted them (#3150). Add invoke_skill and load_skill to the default exempt list and cover the invariant with a regression test. Closes #3163
43ac837 to
bbddedd
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
UtilityScoringConfig::default()hadexempt_tools: Vec::new(), causing the utility scorer to blockinvoke_skillandload_skillcalls withRetrieve/RespondverdictsAdversarialPolicyConfig::default_exempt_tools()behaviour from fix(skills,tools): exempt invoke_skill from policy gates and fix plugin hot-reload #3150utility_scoring_default_exempt_tools_contains_skill_opsTest plan
cargo nextest run -p zeph-tools -E 'test(utility_scoring_default_exempt)'— passesecho "use the /help skill" | cargo run --features full -- --config .local/config/testing.toml— skill executes without utility gate blockCloses #3163