---
title: Reviewer Agent
description: The Reviewer agent role, multi-criteria scoring, and revision control.
sidebar:
  order: 5
  label: Reviewer Agent
---

## The Reviewer Agent (`◆`)

The **Reviewer** acts as the senior software engineering lead on the pipeline. It evaluates the combined output of the Planner, Coder, and Tester before any code is committed.

---

## Evaluation Criteria & Scoring

The Reviewer scores the change across 4 core dimensions on a scale from 1 to 10:

1. **Correctness (1–10):** Does the code accurately satisfy all requirements without introducing regressions?
2. **Code Quality (1–10):** Is the code idiomatic, clean, maintainable, and conformant with the project's conventions?
3. **Test Coverage (1–10):** Are edge cases, error conditions, and happy paths adequately verified?
4. **Spec Adherence (1–10):** Did the Coder follow the constraints defined in the `TaskSpec`?

---

## Verdicts & Revision Loops

The Reviewer issues one of three verdicts in its `ReviewVerdict` artifact:

* **`Approved`:** The code meets quality and correctness thresholds. NIKI commits the branch and writes `report.md`.
* **`RevisionNeeded`:** Issues were discovered. The Reviewer provides specific actionable feedback and kicks off revision round $N+1$ back to the Coder (up to `general.max_revision_rounds`).
* **`Rejected`:** Fundamental architectural flaw or irreparable defect. The task terminates with a descriptive audit report.

```toml
[agents.reviewer]
provider    = "anthropic"
model       = "claude-sonnet-4-20250514"
max_tokens  = 8192
temperature = 0.1
```