Create a remote semantic reviewer — remote

remote_reviewer() creates a reviewer function backed by an HTTP endpoint. It is intended for teams that already have a policy service, review gateway, or hosted model wrapper that returns llmshieldr-compatible JSON findings.

Usage

remote_reviewer(
  url,
  headers = list(),
  body_field = "prompt",
  response_path = NULL,
  timeout = 30
)

Arguments

url: Endpoint URL.
headers: Named character vector or list of HTTP headers.
body_field: JSON field name used for the reviewer prompt.
response_path: Optional character vector path to extract from a JSON response, such as c("data", "findings").
timeout: Request timeout in seconds.

Value

A reviewer function suitable for reviewer = in scan_prompt(), scan_output(), scan_context(), or secure_chat().

Details

The returned function accepts the reviewer prompt generated by llmshieldr and sends a JSON body to url. By default, the body is:

{"prompt": "..."}

The endpoint may return either a JSON response body or plain text containing JSON. If the response body is JSON and response_path is supplied, the value at that path is extracted before returning to the scanner. Otherwise the response body is returned as text and parsed by llmshieldr's semantic-review JSON extraction logic.

This helper requires the optional httr2 package and performs no network calls until the reviewer function is invoked.

Examples

if (FALSE) { # \dontrun{
reviewer <- remote_reviewer(
  "https://policy.example.com/review",
  headers = c(Authorization = "Bearer <token>")
)

scan_prompt("Review me", reviewer = reviewer, checks = "llm")
} # }