ModelRefs / Code Review Assistant — Canonical Workflow

Code Review Assistant — Canonical Workflow

Code Review Assistant: provisional AI workflow implementation reference with candidate models, providers, tools, and architecture.

Overview

Reviews PRs for security, correctness and style with citation back to your project conventions and prior reviews. Code Review Assistant is a provisional implementation reference with candidate models, providers, tools, benchmarks and deployment patterns to validate on the target workload. Engineered for developer tooling pipelines with reproducible evaluation harnesses, CI/CD integration, and per-commit model versioning. Self-hosted cluster deployment provides full network isolation and GPU scheduling control. Evaluation results are persisted to a metrics store and surfaced in PR review dashboards.

Implementation profile

Categorycoding-models
Implementation maturityproduction
Primary use casescoding-copilot, reasoning
Deployment optionsmanaged-api, hybrid
Architecturesserverless-api, managed-container, self-hosted-cluster

Candidate models with published references

Coverage means the model is a candidate worth evaluating for this workflow, not a ranking or a recommendation. Models whose reference pages are still in review are omitted.

Benchmarks relevant to this workflow

  • HumanEval+ — Function-level code synthesis with extended hidden tests.
  • LiveCodeBench — Fresh competitive programming problems with timestamped contamination guard.

These are the benchmarks whose task shape bears on this workflow. Each one only describes its own protocol and date, so confirm the harness matches your workload before treating a score as evidence.

Continue your research

Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Code Review Assistant — Canonical Workflow.