Pin p5 verdict, empty compose_report, absolute source-hint refusal (closes #13) - #19
Merged
Merged
Conversation
…e-hint refusal Three coverage gaps where a real regression would pass the suite: - p5 aggregator (the default that decides every ship/no_ship) had no test pinning its percentile math or the tolerate-one-sub-floor-but-not-two semantics; swapping _p5 for max/mean passed. Now locked. - compose_report with no applicable scenarios resolving to no_ship (fail-safe) was implicit and untested. - The untrusted absolute-path source-hint refusal (ADR-0012, tier2.py) had no test; only .. traversal was covered, so dropping the is_absolute() guard kept the suite green. 6 tests, no behavior change. Closes #13.
🛫 Volo reliability — ❌ NO-SHIPReplayed 7 adversarial scenarios against the agent (threshold ≥ 0.90).
Cost — replayed deterministically at $0 (no live API calls). baseline |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #13. Pure test additions — no behavior change.
Three gaps where a real regression currently passes the suite:
report.py) — the default aggregator deciding every ship/no_ship had no test pinning its percentile math; every existing test used all-1.0 or a forced 0.0 (caught by the separateany_zeroguard), so replacing_p5withmax/meanpassed. Now: direct spread assertions + the tolerate-one-sub-floor-but-not-two semantics (one 0.5 among 20 → ship; two → no_ship).no_shipwas an implicit fail-safe with no test.tier2.py, ADR-0012) — only..traversal was covered, so deleting theis_absolute()guard kept the suite green. Now an absolute path inside base_dir is asserted refused under the untrusted policy (and allowed under trusted).6 tests. Full suite 534 passed, mypy + ruff clean.