AI Code Review

The codeant review command runs an AI-powered code review using an agentic architecture. The agent analyzes your code changes, reads surrounding context from your codebase, and provides detailed suggestions with severity levels.

Basic Usage

# Review all changes (committed + uncommitted) - default
codeant review

# Review only uncommitted changes
codeant review --uncommitted

# Review only staged files
codeant review --staged

# Review only unpushed commits
codeant review --committed

Options

Review Scope

Option	Description
`--all`	Review committed + uncommitted changes (default)
`--committed`	Review only unpushed commits
`--uncommitted`	Review only uncommitted changes
`--staged`	Review only staged files
`--last-commit`	Review the last commit
`--last-n-commits <n>`	Review the last n commits (max 5)
`--base <branch>`	Compare against a specific base branch
`--base-commit <commit>`	Compare against a specific commit SHA

Filtering & Thresholds

Option	Description
`--fail-on <level>`	Fail threshold: `BLOCKER`, `CRITICAL`, `MAJOR`, `MINOR`, `INFO` (default: `CRITICAL`)
`--include <patterns>`	Comma-separated glob patterns to include files
`--exclude <patterns>`	Comma-separated glob patterns to exclude files

CI / Headless Mode

Option	Description
`--headless`	Output clean JSON to stdout (disables spinners and interactive UI)

Use --headless when running inside CI pipelines or AI agents. In this mode:

All results are written to stdout as JSON
Progress and status messages are written to stderr
No interactive prompts are shown

# Use in CI - parse JSON output with jq
codeant review --headless --all | jq '.suggestions[] | select(.severity == "CRITICAL")'

How It Works

The review runs in a multi-phase pipeline:

Phase 1: Per-File Analysis

Each changed file is analyzed independently and in parallel. For each file, the agent:

Receives the diff and full file content
Can use tools to read other files, search the codebase, and explore directory structures
Iterates through up to 5 conversation turns to gather context and form suggestions
Returns file-specific suggestions with severity labels

Agent Tools Available:

Tool	Description
Read	Read file contents with optional line ranges
Glob	Find files matching glob patterns
Grep	Search file contents with regex patterns
LS	List directory contents

Phase 2: Reflector

After all per-file analyses complete, the reflector phase:

Combines all per-file suggestions
Runs a final analysis pass to deduplicate, refine, and prioritize
Produces the final set of code suggestions

Severity Levels

Each suggestion is assigned a severity based on its label:

Label	Severity
`security`	CRITICAL
`bug`	MAJOR
`performance`	MAJOR
`maintainability`	MINOR
`code quality`	MINOR
`best practice`	MINOR

The --fail-on flag determines the exit code:

0 - No suggestions at or above the threshold
1 - Suggestions found at or above the threshold

File Filtering

The review automatically excludes files that are unlikely to benefit from code review: Lock files: package-lock.json, yarn.lock, pnpm-lock.yaml, composer.lock, Gemfile.lock, Cargo.lock, poetry.lock, Pipfile.lock, go.sum Binary/compiled: .exe, .dll, .so, .dylib, .bin, .o, .a, .class, .pyc, .wasm, .jar, .war Media: .png, .jpg, .jpeg, .gif, .svg, .webp, .mp3, .mp4, .wav, .avi, .mov Fonts: .woff, .woff2, .ttf, .eot, .otf Archives: .zip, .tar, .gz, .bz2, .7z, .rar Generated/minified: .min.js, .min.css, .map, .pb Documents: .pdf, .doc, .docx, .xls, .xlsx, .ppt, .pptx System: .DS_Store, Thumbs.db

Size Limits

Maximum file size: 5,000 lines per file
Maximum files per review: 10 unique files

Files exceeding these limits are skipped with a warning.

Examples

# Review all changes with default settings
codeant review

# Review against a specific branch
codeant review --base develop

# Review against a specific commit
codeant review --base-commit abc1234

# Review last 3 commits
codeant review --last-n-commits 3

# Only review TypeScript files, fail on MAJOR and above
codeant review --include '**/*.ts' --exclude '**/*.test.ts' --fail-on MAJOR

# Review staged files only
codeant review --staged

# Review uncommitted changes, include MINOR severity
codeant review --uncommitted --fail-on MINOR

Terminal UI

The review displays a live progress indicator in your terminal:

⠋ Analyzing... (12s)
  Step 2/4: Reviewing src/auth.ts (turn 3/5)

Progress steps:

Init - Initializing review session
Fetch - Gathering diffs and file contents
Analyze - Per-file agent analysis (parallel)
Reflect - Final reflector pass

When complete, suggestions are displayed with color-coded severity and file locations.

Get Started

Scan Center

Code Security

Code Quality

Engineering Metrics

IDE

CLI

CI/CD

Integrations

Rule Reference

How CodeAnt Uses CodeAnt

Resources

AI Code Review

Basic Usage

Options

Review Scope

Filtering & Thresholds

CI / Headless Mode

How It Works

Phase 1: Per-File Analysis

Phase 2: Reflector

Severity Levels

File Filtering

Size Limits

Examples

Terminal UI

​Basic Usage

​Options

​Review Scope

​Filtering & Thresholds

​CI / Headless Mode

​How It Works

​Phase 1: Per-File Analysis

​Phase 2: Reflector

​Severity Levels

​File Filtering

​Size Limits

​Examples

​Terminal UI

Basic Usage

Options

Review Scope

Filtering & Thresholds

CI / Headless Mode

How It Works

Phase 1: Per-File Analysis

Phase 2: Reflector

Severity Levels

File Filtering

Size Limits

Examples

Terminal UI