backend-agent
d7e007a4ea
Replace cloud-based LLM providers (Anthropic/OpenAI) with a local Ollama sidecar running lightweight quantized models (qwen2.5-coder:1.5b as primary, phi3:mini as fallback). All generation stays under 60s on CPU, data never leaves the network, and there are zero API costs. Updated: architecture diagram, component description, technology choices, project layout, docker-compose, env vars, and consequences sections.
stub-service
Go-based HTTP stub/mock service with Web UI and LLM-powered configuration generation.
An alternative to Mountebank focused on simplicity, a modern web interface, and AI-assisted stub creation.
Status
Planning phase — see ADR-001 for the architecture decision record.
Features (planned)
- HTTP/HTTPS stub server with rich request matching (equals, contains, regex, JSONPath, XPath)
- REST API for full CRUD management of imposters and stubs
- Web UI for browsing, creating, and editing mock configurations
- Real-time request log viewer
- LLM integration for natural-language stub generation
- Proxy mode with record/replay
- Response templating via Go templates
- File-based or embedded database persistence
- Docker-ready deployment
License
Internal use.