PR review findings

This commit is contained in:
Dennis Meister
2026-02-18 16:17:34 +01:00
parent ed531f401d
commit ea3a1d03f7
3 changed files with 30 additions and 6 deletions
@@ -21,9 +21,10 @@ Both **GitLab.com** and **self-hosted GitLab instances** are supported.
### Step 1: Connect GitLab
You can connect using **OAuth** or a **Personal Access Token (PAT)**.
You can connect using **OAuth** or a **Personal Access Token (PAT)**. Choose the method that matches your GitLab setup:
#### Option A: OAuth (GitLab.com)
{% tabs %}
{% tab label="OAuth (GitLab.com)" %}
1. Go to the **Integrations** page:
- **Personal**: [app.kilo.ai/integrations/gitlab](https://app.kilo.ai/integrations/gitlab)
@@ -32,7 +33,8 @@ You can connect using **OAuth** or a **Personal Access Token (PAT)**.
3. Authorize the application on GitLab
4. You'll be redirected back to Kilo with the connection active
#### Option A: OAuth (Self-Hosted)
{% /tab %}
{% tab label="OAuth (Self-Hosted)" %}
For self-hosted GitLab instances using OAuth, you need to register an OAuth application first:
@@ -47,7 +49,8 @@ For self-hosted GitLab instances using OAuth, you need to register an OAuth appl
5. Enter your **Instance URL**, **Client ID**, and **Client Secret**
6. Click **Connect** and authorize
#### Option B: Personal Access Token
{% /tab %}
{% tab label="Personal Access Token" %}
1. In GitLab, go to **User Settings → Access Tokens**
2. Create a token with the `api` scope
@@ -58,6 +61,9 @@ For self-hosted GitLab instances using OAuth, you need to register an OAuth appl
> PAT tokens cannot be refreshed automatically. When your token expires, create a new one in GitLab and reconnect in Kilo.
{% /tab %}
{% /tabs %}
### Step 2: Configure the Review Agent
1. Go to **Code Reviews**:
@@ -7,6 +7,14 @@ description: "Automate code reviews with AI assistance"
Kilo's **Code Reviews** feature automatically analyzes your pull or merge requests using an AI model of your choice. It can review code the moment a PR/MR is opened or updated, surface issues, and provide structured feedback across performance, security, style, and test coverage.
## What Code Reviews Enable
- Automated AI review on every pull request
- Consistent feedback based on your teams standards
- Automatic detection of bugs, security risks, and anti-patterns
- Deep reasoning over changed files, diffs, and repo context
- Customizable review strictness and focus areas
## Supported Platforms
| Platform | Integration Type | Details |
@@ -68,7 +76,11 @@ When a pull request or merge request is opened or updated:
1. The Review Agent receives the PR/MR metadata, diff, and file context.
2. The selected model analyzes all changes.
3. The agent applies your chosen review style and focus areas.
4. It generates a structured review with: - Inline comments - Summary findings - Suggested fixes - Risk and severity tagging
4. It generates a structured review with:
- Inline comments
- Summary findings
- Suggested fixes
- Risk and severity tagging
5. Reviews respect the **maximum time limit** you set.
6. Only repositories youve selected will trigger automatic analysis.
@@ -483,7 +483,13 @@ module.exports = [
// ============================================
{
source: "/docs/advanced-usage/code-reviews",
destination: "/docs/automate/code-reviews",
destination: "/docs/automate/code-reviews/overview",
basePath: false,
permanent: true,
},
{
source: "/docs/automate/code-reviews",
destination: "/docs/automate/code-reviews/overview",
basePath: false,
permanent: true,
},