# Settings (https://tenki.cloud/docs/reviewer/settings)

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

Tenki Code Reviewer exposes a small set of configuration options to control when it runs and how much signal it produces.



![TenkiCodeReviewerSettings](https://tenki.cloud/images/reviewer/tcr-settings-2.png)

Severity Threshold: [#severity-threshold]

Controls which findings are surfaced in the review.

You can choose to include the following severity levels:

* **High**
* **Medium**
* **Low**

By default, only **High** severity findings are enabled.

Enabling additional levels will surface more detailed and verbose feedback, including non-blocking issues and minor observations.

**Use this when:**

* You want minimal, merge-blocking signal (High only)
* You want broader coverage during audits, refactors, or hardening phases

Automatic Review [#automatic-review]

Controls **when the agent runs on a Pull Request**.

Available modes:

* **On**: runs on every PR update
* **Off**: runs only when the agent is explicitly mentioned or tagged in the PR

Comment Detail Level [#comment-detail-level]

Controls **the level of verbosity** of the review.

Available modes:

* **Concise**: A brief overview of the vulnerabilities.
* **Standard**: The default option; provides a few sentences with enough detail about the issues or vulnerabilities detected.
* **Detailed**: The most comprehensive option; offers in-depth information about each issue or vulnerability found.

Ignore Usernames [#ignore-usernames]

Allows excluding specific authors from automated reviews.

You can add one or more GitHub usernames to prevent Gary from running on PRs created by those users.

Common use cases:

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