Pablan, as it stands

Self-hosted knowledge management for SMEs: a split-screen Markdown editor
whose sections an LLM refines while you write, and RAG question answering
over the documents that result. FastAPI + Postgres/pgvector on the back,
SvelteKit on the front, everything OpenAI-compatible and self-hostable.

Squashed into a single commit; the development history stays local.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CA43ZJda8Rbp2hKXNy8f6b

backend/app/api/authoring/__init__.py

@@ -0,0 +1,18 @@
+"""The authoring API: the model's help while someone writes.
+
+Three endpoints under `/documents`, all owner-scoped: refine the section at the
+cursor (streamed), suggest a title for a finished draft, and suggest which
+existing document a capture should extend. What they share is `grounding` — the
+permission-filtered look at what the company already wrote.
+
+`suggest-similar` has a static path and is registered before the refine module
+so it cannot be read as a document id.
+"""
+
+from fastapi import APIRouter
+
+from app.api.authoring import refine, suggest
+
+router = APIRouter()
+router.include_router(suggest.router)
+router.include_router(refine.router)