Claim approved
Business stage set to awaiting_site_generation in the same transaction as approval.
claims-approval.tsOne env flag, GENERATION_MODE, decides which path actually runs. local reuses the same automated agent already deploying this app every 30 minutes — it runs the ep044_group skills itself, using your Claude subscription, at no per-call cost. hosted is the Render cron + LLM-API loop already built in lib/generation/. Only one path is ever active; both produce identical output at the same GitHub location and both hand back to the same three endpoints, so the rest of the pipeline never needs to know which mode built a given site.
A business enters the queue the moment claim approval fires (already built).
Business stage set to awaiting_site_generation in the same transaction as approval.
claims-approval.tsAny consumer — local agent or hosted cron — can see it.
GET …/queuelocal → left path runs, hosted path is inert.
The same agent already redeploying this app every 30 minutes also runs this loop on its own cycle.
Its normal 30-min pass now also calls the queue endpoint.
GET …/queueSame normalize-and-match this session already built for the hosted path.
lib/generation/skill-loader.tsNo LLM API call — the agent is the model, reasoning directly against SKILL.md + business data + images, under your existing subscription.
skills/ep044_group/…Same output location the hosted path would use — GitHub Pages serves either identically.
epics/ep_006_website_rebuilds/redesigns/<slug>/Already built — advances the pipeline stage.
POST …/completeAlready built — preview-ready email.
POST …/notifySame skill and image inputs, but the model call goes over HTTP with metered billing — the path for once there are paying clients and no one's watching a subscription session.
Every 15 minutes, independent of any local session.
render.yaml → ep047-site-generationNo-ops cleanly if LLM_PROVIDER/key unset.
lib/generation/config.tsOne prompt, one structured JSON-files response — no tool-use loop yet.
lib/generation/llm-client.tsDeliberately not auto-committed/pushed — left as a confirmed step.
run-generation.tsSame seam as local mode.
POST …/completeSame seam as local mode.
POST …/notifycomplete endpoint, which advances the pipeline stage — if both ran against the same queue at once, a business could get double-generated (or the second run's completion call could silently overwrite the first). GENERATION_MODE is a hard either/or switch, not a preference; whichever path is not selected must exit immediately without touching the queue at all.