test(eval): add safety invariant check for PR approvals#95
Open
dembrane-sam-bot wants to merge 1 commit into
Open
test(eval): add safety invariant check for PR approvals#95dembrane-sam-bot wants to merge 1 commit into
dembrane-sam-bot wants to merge 1 commit into
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What this changes
Adds a structural test in
tests/eval/test_structural.pyto verify thatsrc/capabilities/github.mdexplicitly retains the safety boundary forbidding Sam from approving its own PRs or repository.This test is robust across both the existing
mainbranch and the pending PR #91 branch (it asserts on either of the safety definitions).Context
Opened in response to daily-maintenance Opus mentor review on 2026-05-27. Loosening prose-only safety rules without corresponding structural gates/invariants is a high-risk failure mode (violating the 'prose explains, runtime enforces' design pattern from
self-maintenance.md). This test acts as a structural gate.Confidence
Confidence: high. The test evaluates and runs cleanly on both the existing main state and the pending PR #91 branch state.