ops-copilot

A minimal FastAPI service for chat operations with structured logging and tracing.

About This Project

This project was entirely built by an AI agent following professional engineering standards. The templates and standards used for development are documented in docs/engineering/, including:

• AI_COMPOSER_TEMPLATE.md: Standardized template for AI-assisted development
• PR_REVIEW_CHECKLIST.md: Checklist for consistent PR reviews
• ARCHITECTURE_DECISIONS.md: Record of architectural choices
• EVAL_STRATEGY.md: Evaluation and testing standards

Setup

1. Create a virtual environment (optional but recommended):

   python3 -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate

2. Install dependencies:

   pip install -r requirements.txt

Running the Server

uvicorn api.main:app --reload

The API will be available at http://localhost:8000

Running Tests

pytest

Tests run automatically on pull requests via GitHub Actions CI.

Docker

Build the Docker image

docker build -t ops-copilot .

Run the container

docker run -p 8000:8000 ops-copilot

The API will be available at http://localhost:8000

API Endpoints

POST /chat

Send a chat message and receive a stubbed response.

Request Body:

{
  "user_message": "hello",
  "thread_id": null
}

Response:

{
  "reply": "stubbed response",
  "trace_id": "uuid-string",
  "model": "stub-model-v0"
}