Files
family_home_lab/docs
Sam Rolfe 2609ab5286 dsh: offer the local .27 Ollama models in the chat model dropdown
The dropdown is built from the hardcoded MODEL_CHOICES list in app.py, not from
OmniRoute, so 'ollama/qwen2.5*' existed upstream but could never appear in DSH.

- add ollama/qwen2.5:14b and ollama/qwen2.5-coder:14b to MODEL_CHOICES + MODEL_LABELS
- labels note that Ollama must be started first, since it now boots off on .27
- docs/dsh-architecture.md: new section on model selection, incl. the rebuild
  requirement (app.py is baked into the image via COPY . .) and the ordering trap
  that a model can be live in OmniRoute yet invisible in DSH

Verified: /api/models lists both ids on 3081-3084, and real streamed replies come
back from both local models through DSH.
2026-10-12 17:05:25 +11:00
..

Family Home Lab Technical Documentation

This directory contains architectural specifications, component manuals, integration tables, and network registries for the Family Home Lab ecosystem.

Core Technical Reference Specs

  • DeepSeek Harness (DSH) Architecture: Multi-instance chat engine, per-user container allocation (sam, jo, harry, finn), ports (3081–3084), JSON session persistence, multi-model routing table (OmniRoute, OpenRouter, Whisper, Jervis Voice Agent), CSP framing, and API endpoints.

  • Console Portal Architecture: FastAPI application spec, user database schema, access control entitlement flags (can_chat, can_image, can_audio, can_docs), tool catalogue structure (tools.py), host-side service-controller bridge, ON/OFF RAM management, and Garage S3 file integration.

  • Host Network & Port Registry: Single source of truth network topology and port allocations across hosts .13 (containers/models), .35 (Caddy/Gitea/Outline), .27 (dev workstation), and .51.


Component Plans & Features