r2r-jev

asks Jev two `Noul` checks per tool call (beyond scope, destructive) and admits each judgment as Evidence that can degrade Trust, Delegation, and Authorization until a human override repairs the relation, so later calls inherit the history; includes a stateless-vs-stateful comparison with a scenario adversarial to persistence.

OWNER

Thneoly

INDUSTRY

Agent governance

WHAT IT DECIDES

CHOICE

Picks one option from a fixed set

SCORE

Rates against ordered levels

NOUL

Answers a yes / no question

Inferred from this project's own one-line summary in the community list — it reads as a NOUL decision. Read the source to confirm.

THE SHAPE OF A NOUL CALL

A generic skeleton for this question type, not this project's actual code.

from typesafe import TypeSafe

ts = TypeSafe()
result = ts.evaluate(
    state=tool_call,
    questions={
        "is_risky": {
            "type": "noul",
            "instructions": "Could this call delete or overwrite user data?",
        }
    },
)
if result["is_risky"] and result["is_risky_confidence"] > 0.6:
    escalate_to_human(tool_call)

MORE IN Verification & Guardrails

jev-reviewstaged code-review workflow and local dashboard where Jev gates each review stage before a change advances.is-maliciousasks Jev `Noul` checks about source and build files, escalates suspicious chunks for a second pass, and returns implicated files and lines before execution.pi-jevadds a measured tool-call gate to the Pi coding agent so risky calls are checked by Jev before execution.OpenWorkwires Jev into its eval testkit as a verification judge so agent-produced work is gated by typed verdicts rather than a text model.