jev_gate_action
Checks an action before execution to flag destructive, outward-facing, or credential-touching scope and mismatch with the user request, returning allow, confirm, or block.
Instructions
Advisory pre-flight check on an action you are about to take: judges whether it is destructive, outward-facing or credential-touching, how far it reaches, and how it relates to what the user asked for — then returns allow / confirm / block from a deterministic policy in code.
NOT A SECURITY BOUNDARY. It is a judgment layer that catches plausible mistakes, and Jev is not hardened against adversarial text: an action or context written to argue for its own approval can shift the result. Never rely on it to contain untrusted input, and never let allow stand in for a real permission check.
Use it just before something you cannot cheaply undo: deleting or overwriting files, git history rewrites, installs, deploys, messages, payments, anything touching an external system.
Pass action as the concrete call, not a paraphrase: one line with the tool name and arguments, or the fields {tool, command, file_path, target_paths, …}, which scores scope better. Pass user_request in the user's own words, as a string or {latest, previous}.
confirm means ask the user first. block means it looks both unrelated to the request and consequential; re-read the request rather than retrying.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"action": "<action>",
"user_request": "<user_request>"
},
"name": "jev_gate_action"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | Exactly what you are about to do, including the tool name and its arguments. | |
| context | No | Optional short context: the working directory, the task, the relevant prior step. | |
| thresholds | No | Override the server's configured gating thresholds for this call only. | |
| user_request | Yes | What the user actually asked for, in their words. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | Yes | The versioned model id that actually answered. | |
| scope | Yes | What the scope reading was made of. `signals.in_scope` is `step + requested`. | |
| usage | Yes | Token usage. Jev charges for input tokens only. | |
| reasons | Yes | Which policy rules fired, in plain language. | |
| signals | Yes | Raw P(yes) for each signal. Near 0.5 means the model is unsure. | |
| decision | Yes | allow: proceed. confirm: ask the user first. block: do not run it. | |
| latency_ms | Yes | Wall-clock time for the underlying API call(s), including retries. | |
| thresholds | Yes | ||
| blast_radius | Yes | How far the effects reach. 0 = read-only, 3 = production or other people. | |
| signal_leans | Yes | How each signal was read: yes / no / uncertain, using the auto threshold. |