feat: add AI catalog description generation

AGENTS.md

@@ -76,12 +76,14 @@ frontend (React/SSE) → backend (Fastify) → pi --mode rpc → tht/harness →
   There is no verbatim transcript store. A resumed Pi process rebuilds context from
   `tht session show <id>` + the on-disk artifacts.
 
-- **The backend is a thin bridge with no database.** `ThtRunner` shells the Python workflow `tht`
-  subcommands inside `core`;
+- **The backend bridges sessions and owns the installation-local metadata catalog.** `ThtRunner`
+  shells the Python workflow `tht` subcommands inside `core`;
   `PiProcessManager` runs one Pi child per session and bridges its RPC stream;
   `SessionBridge` maps Pi RPC events → client events (`ui_request`/`text_delta`/`info`);
-  `SseHub` fans them out over SSE to the browser. App settings live in a JSON file
-  (`backend/data/settings.json`), not a DB.
+  `SseHub` fans them out over SSE to the browser. The separate PostgreSQL catalog stores database
+  metadata and sequential AI description-generation runs. Description generation samples the DWH
+  through read-only connectors and calls a short-lived Python LiteLLM helper; it does not use Pi or
+  expose a public CLI command. App settings still live in `backend/data/settings.json`.
 
 - **Human-in-the-loop gate contract.** The model proposes; a human reviewer decides at gates
   via widgets (`reviewer_select` = single pick — a chosen option carrying a `decision` payload