# Settings (https://luxor.ai/docs/reviewer/settings)

> For the complete documentation index, see [llms.txt](https://luxor.ai/llms.txt)

Code Reviewer exposes a small set of configuration options to control when it runs and how much signal it produces, on GitHub and Cursor Origin.

Open **Code Reviewer → Configuration** to change these settings. They apply to reviews on both GitHub and [Cursor Origin](https://luxor.ai/docs/reviewer/cursor-origin.md). Select **Save Changes** to apply your edits, or **Reset** to discard them.

<img src="getAsset(&#x22;/images/reviewer/v2/settings.png&#x22;)" alt="Code Reviewer configuration with Scope selector and review settings" />

Every setting applies workspace-wide by default. Use the **Scope** selector to override any setting for a single repository. See [Per-repository overrides](https://luxor.ai/docs/reviewer/repo-management.md#per-repository-overrides).

## Who can run reviews

Every member of your workspace can trigger a review — automatically when a pull request is opened or updated, or
manually by mentioning `@luxor-reviewer`. There are no per-user seats to assign.

Reviews are billed at **$1.00 each** on both providers and draw from your workspace balance, so what gates reviews is your
[balance](https://luxor.ai/docs/account/billing.md) and any spending limit you have set, not a per-user allowance. To keep specific
authors from triggering automatic reviews, add them to [Ignore Usernames](#ignore-usernames).

## Severity Threshold

Which severity levels the reviewer reports: **Critical**, **High**, **Medium**, and **Low**. At least one level must stay selected.

All four are selected by default, so reviews surface the full range of findings, including minor observations. Deselect lower levels to narrow reviews to higher-severity issues.

## Automatic Review

Whether the reviewer runs on new pull requests without being asked.

* **On** (default): reviews pull requests when they are opened or marked ready for review
* **Off**: reviews only when someone mentions `@luxor-reviewer`

## Review on Push

Whether the reviewer reviews again when new commits are pushed to an open pull request. Available only when Automatic Review is on. Each re-review counts toward your usage.

* **On**: reviews the pull request again after each push
* **Off** (default): reviews once and doesn't re-run on later pushes

## Approve on Clean Review

Whether the reviewer approves the pull request when a review finds nothing worse than nitpicks.

* **On** (default): approves the pull request when no blocking findings are open
* **Off**: comments on findings but never records an approval

## Comment Detail Level

How detailed review comments and summaries are.

* **Concise** — Brief findings.
* **Standard** (default) — Fix guidance.
* **Detailed** — Full explanations. Each finding also carries a suggested fix (and a suggested code change where one applies), and the summary adds a severity table and the list of files reviewed.

## PR Walkthrough

Whether the reviewer adds a walkthrough of the change to the pull request description.

* **On**: adds a walkthrough to the description and keeps it up to date
* **Off** (default): leaves the description untouched

## Ignore Usernames

Skips automatic reviews for pull requests opened by these authors. `dependabot[bot]` and `renovate[bot]` are ignored by default.

* On **GitHub**, enter usernames. `dependabot` also matches `dependabot[bot]`.
* On **Cursor Origin**, enter the author's email address.

Common use cases:

* Bot or automation accounts
* Experimental or sandbox contributors
* Temporary exclusions during testing