8 Commits
Author SHA1 Message Date
Violin 3807d22eaa fix(benchmark): evidence-gated scorer contract, false-positive discriminators, runner validity
- Confirm Validated hypotheses via canonical FIND-NNN.md matched in live-app
  terms (METHOD + endpoint route) alongside execution bundles
- require/require_any discriminators for shared-endpoint challenges;
  absence-type scoring for no-rate-limiting
- Runner: closeout timeout is a soft warning, not run invalidation
- ai_judge: whitelist legitimate closeout artifacts in schema-drift audit
- Align version surfaces to 3.1.0; move pyyaml to runtime deps

Calibration: known-good 20/20, known-bad 0/0. Latest run re-scored 4 -> 9.
2026-08-10 20:52:02 +01:00
Violin 48a4f214d6 feat(guard): add receipt integrity verifier, fail-closed state parsers, and guard runtime tests 2026-08-10 08:54:56 +01:00
Violin d7e139c486 feat: implement violin_guard plugin with secure execution adapters, terminal policies, and pentest skill frameworks 2026-08-08 13:29:11 +01:00
Violin 4b21dce94a feat: harden benchmark evaluation and guard runtime 2026-08-08 13:29:11 +01:00
DanandGitHub 5071b9689f docs(release): align workflow instructions, hypothesis discipline, and release v3.0.1 (#64)
Merge dev into master
2026-08-04 17:18:44 +01:00
Violin b274364118 feat: implement violin_guard plugin for secure pentest execution, target policy enforcement, and workflow orchestration 2026-07-25 14:13:38 +01:00
Violin dd557974a3 Require proof-backed finding self-review 2026-07-19 01:24:04 +01:00
Violin 5870509fdb feat: implement violin_guard plugin for centralized command execution auditing, terminal policy enforcement, and history tracking. 2026-07-17 20:14:20 +01:00