Skip to content

Pin p5 verdict, empty compose_report, absolute source-hint refusal (closes #13) - #19

Merged
abhay-codes07 merged 1 commit into
mainfrom
test/reliability-and-security-gaps
Jul 12, 2026
Merged

Pin p5 verdict, empty compose_report, absolute source-hint refusal (closes #13)#19
abhay-codes07 merged 1 commit into
mainfrom
test/reliability-and-security-gaps

Conversation

@abhay-codes07

Copy link
Copy Markdown
Owner

Closes #13. Pure test additions — no behavior change.

Three gaps where a real regression currently passes the suite:

  1. p5 verdict aggregator (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 separate any_zero guard), so replacing _p5 with max/mean passed. Now: direct spread assertions + the tolerate-one-sub-floor-but-not-two semantics (one 0.5 among 20 → ship; two → no_ship).
  2. Empty compose_report — no applicable scenarios resolving to no_ship was an implicit fail-safe with no test.
  3. Untrusted absolute-path source-hint refusal (tier2.py, ADR-0012) — only .. traversal was covered, so deleting the is_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.

…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.
Copilot AI review requested due to automatic review settings July 12, 2026 17:47

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

@github-actions

Copy link
Copy Markdown

🛫 Volo reliability — ❌ NO-SHIP

Replayed 7 adversarial scenarios against the agent (threshold ≥ 0.90).

Metric Score
Trajectory determinism 1.000
Decision determinism 1.000
Faithfulness 0.000
Consistency under repetition 1.000

Cost — replayed deterministically at $0 (no live API calls).

baseline 1783878455633-708b3f87-c5f9-4c0b-831b-75a0646e6928 • generated by Volo

@abhay-codes07
abhay-codes07 merged commit c58bc79 into main Jul 12, 2026
3 of 4 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Add tests: p5 verdict aggregator, absolute-path source-hint refusal, empty compose_report

2 participants