Skip to content

v4.22.0 — ship the verify caveat with its remedy attached

Choose a tag to compare

@rbinar rbinar released this 16 Aug 23:36
· 3 commits to main since this release
f998d71

Changed

  • The injected policy now states the remedy in the same breath as the verify caveat.
    Measured across two sessions that received the policy and never once used the runner
    (5,799 and 2,361 Bash calls, 732 and 220 of them gate-able test/build/lint commands), the
    runner was considered exactly once and rejected like this: "--verify only says the tests
    pass, not that behavior was preserved — so I won't delegate the verification." That inverts
    the rule. The caveat exists because verification stays with the orchestrator, which is a
    reason to re-measure after delegating, not a reason to keep the work inline. Quoted
    half, the caveat became a veto. The policy paragraph now carries the remedy attached, and a
    test pins the pairing so it cannot be dropped silently. The wording change is bounded by the
    existing 160-word ceiling test, which was not modified (148 words with everything enabled).