docs: installing CoderAI as a GPU-less RunPod orchestrator

An operator guide for the deployment shape the Digesta host uses: no local
GPU, models rented per request, scaled by the pool, billed into a capped
ledger. Covers install and signature check, the sub-path nginx config, the
global caps to set BEFORE adding a model, the per-model block, the four
scaling numbers plus the two pod-side admission ones that otherwise cap a
dedicated card at ~6 pages/s, the warm-pod schedule, all three layers of
cost control (caps, GUI, /v1/runpod/spend with an admin-scoped key), the
call shapes, and a symptom table.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

docs/README.md

@@ -34,5 +34,6 @@ reference; these are the deep dives.
 
 | Doc | Subject |
 |---|---|
+| [orchestrator-runpod-guide.md](orchestrator-runpod-guide.md) | Install CoderAI as a **GPU-less RunPod orchestrator**: register models, scale pods, watch the cost. The operator's path for a host with no GPU |
 | [install-from-packages.md](install-from-packages.md) | `docker pull ghcr.io/nextime/coderai` — the full image and the nineteen capability images, Linux, Windows, offline |
 | [reverse-proxy-nginx.md](reverse-proxy-nginx.md) | nginx at root, on a subdomain, or under a sub-path |