Implement intelligent agent assignment algorithm that selects the optimal agent for each issue based on context capacity, difficulty, and cost. Algorithm: 1. Filter agents that meet context capacity (50% rule - agent needs 2x context) 2. Filter agents that can handle difficulty level 3. Sort by cost (prefer self-hosted when capable) 4. Return cheapest qualifying agent Features: - NoCapableAgentError raised when no agent can handle requirements - Difficulty mapping: easy/low->LOW, medium->MEDIUM, hard/high->HIGH - Self-hosted preference (GLM, minimax cost=0) - Comprehensive test coverage (100%, 23 tests) Test scenarios: - Assignment for low/medium/high difficulty issues - Context capacity filtering (50% rule enforcement) - Cost optimization logic (prefers self-hosted) - Error handling for impossible assignments - Edge cases (zero context, negative context, invalid difficulty) Quality gates: - All 23 tests passing - 100% code coverage (exceeds 85% requirement) - Lint: passing (ruff) - Type check: passing (mypy) Refs #145 Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Mosaic Coordinator
FastAPI webhook receiver for Gitea issue events, enabling autonomous task coordination for AI agents.
Overview
The coordinator receives webhook events from Gitea when issues are assigned, unassigned, or closed. It verifies webhook authenticity via HMAC SHA256 signature and routes events to appropriate handlers.
Features
- HMAC SHA256 signature verification
- Event routing (assigned, unassigned, closed)
- AI-powered issue metadata parsing (using Anthropic Sonnet)
- Context estimation and agent assignment
- Dependency tracking (blocks/blocked_by)
- Comprehensive logging
- Health check endpoint
- Docker containerized
- 95%+ test coverage
Development
Prerequisites
- Python 3.11+
- pip or uv package manager
Setup
# Install dependencies
pip install -e ".[dev]"
# Run tests
pytest
# Run with coverage
pytest --cov=src --cov-report=html
# Type checking
mypy src/
# Linting
ruff check src/
Running locally
# Copy environment template
cp .env.example .env
# Edit .env with your values
# GITEA_WEBHOOK_SECRET, GITEA_URL, ANTHROPIC_API_KEY
# Run server
uvicorn src.main:app --reload --port 8000
API Endpoints
POST /webhook/gitea
Receives Gitea webhook events.
Headers:
X-Gitea-Signature: HMAC SHA256 signature of request body
Response:
200 OK: Event processed successfully401 Unauthorized: Invalid or missing signature422 Unprocessable Entity: Invalid payload
GET /health
Health check endpoint.
Response:
200 OK: Service is healthy
Environment Variables
| Variable | Description | Required | Default |
|---|---|---|---|
GITEA_WEBHOOK_SECRET |
Secret for HMAC signature verification | Yes | - |
GITEA_URL |
Gitea instance URL | Yes | - |
ANTHROPIC_API_KEY |
Anthropic API key for issue parsing | Yes | - |
LOG_LEVEL |
Logging level (debug, info, warning, error) | No | info |
HOST |
Server host | No | 0.0.0.0 |
PORT |
Server port | No | 8000 |
Docker
# Build
docker build -t mosaic-coordinator .
# Run
docker run -p 8000:8000 \
-e GITEA_WEBHOOK_SECRET="your-secret" \
-e GITEA_URL="https://git.mosaicstack.dev" \
-e ANTHROPIC_API_KEY="your-anthropic-key" \
mosaic-coordinator
Testing
# Run all tests
pytest
# Run with coverage (requires 85%+)
pytest --cov=src --cov-report=term-missing
# Run specific test file
pytest tests/test_security.py
# Run with verbose output
pytest -v
Architecture
apps/coordinator/
├── src/
│ ├── main.py # FastAPI application
│ ├── webhook.py # Webhook endpoint handlers
│ ├── parser.py # Issue metadata parser (Anthropic)
│ ├── models.py # Data models
│ ├── security.py # HMAC signature verification
│ ├── config.py # Configuration management
│ └── context_monitor.py # Context usage monitoring
├── tests/
│ ├── test_security.py
│ ├── test_webhook.py
│ ├── test_parser.py
│ ├── test_context_monitor.py
│ └── conftest.py # Pytest fixtures
├── pyproject.toml # Project metadata & dependencies
├── .env.example # Environment variable template
├── Dockerfile
└── README.md
Related Issues
- #156 - Create coordinator bot user
- #157 - Set up webhook receiver endpoint
- #158 - Implement issue parser
- #140 - Coordinator architecture