Abide
reads every edit a coding agent makes and has Jev flag rule violations, with the project reporting that an independent reviewer confirmed 10 of the 39 flagged edits and 11 of the 15 flagged turns.
它做什么判断
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.
NOUL 调用长什么样
这是该提问类型的通用骨架,不是这个项目的真实代码。
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)更多校验与防护栏项目
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.