docs/api.md

API Documentation

Base URL

http://localhost:8000/api/v1

Endpoints

Health Check

GET /health

Response:

{
  "status": "ok",
  "message": "AI Code Review Agent is running"
}

---

Full Analysis

POST /analyze

Request:

{
  "github_url": "https://github.com/username/repository"
}

Response: EngineeringReport object

---

Quick Analysis

POST /quick-analyze

Request:

{
  "github_url": "https://github.com/username/repository"
}

Response: RepositoryResponse object

Interactive Docs

Visit http://localhost:8000/docs for Swagger UI

Rate limits

All limits are applied per API key (via X-API-Key header). Requests without a key are limited by IP address.

Endpoint	Limit	Reason
POST /api/v1/analyze	5 req/min	Full pipeline — LLM calls, clone, static analysis
POST /api/v1/analyze/async	20 req/min	Queue submission only — fast and cheap
GET /api/v1/jobs/{id}	120 req/min	Read-only status poll
GET /api/v1/health	unlimited	Healthcheck — no limit applied
GET /metrics/prometheus	unlimited	Prometheus scrape — no limit applied

When a limit is exceeded the API returns 429 Too Many Requests with a Retry-After header indicating when the client may retry.