feat: setup dataset enrichment app codebase and scripts

backend/config.py

@@ -0,0 +1,39 @@
+"""Paths and settings. Everything is environment-driven so the same image runs
+locally and in Docker without code changes (REQ-072)."""
+
+import os
+
+from dotenv import load_dotenv
+
+load_dotenv()
+
+# huggingface_hub reads HF_TOKEN / HUGGING_FACE_HUB_TOKEN; accept either name in
+# .env so pasting a token under the obvious name just works.
+if os.environ.get("HF_TOKEN") and not os.environ.get("HUGGING_FACE_HUB_TOKEN"):
+    os.environ["HUGGING_FACE_HUB_TOKEN"] = os.environ["HF_TOKEN"]
+
+REPO_ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+DATA_DIR = os.path.abspath(os.environ.get("APP_DATA_DIR", os.path.join(REPO_ROOT, "data")))
+PROJECTS_DIR = os.path.join(DATA_DIR, "projects")
+DB_PATH = os.path.join(DATA_DIR, "app.db")
+
+# Where the video archive is mounted. Projects store a path relative to nothing —
+# they store an absolute one — but this is the default the UI starts browsing from.
+VIDEO_ROOT = os.path.abspath(os.environ.get("VIDEO_ARCHIVE", os.path.join(DATA_DIR, "archive")))
+
+# Vite dev server needs cross-origin access; in Docker nginx proxies /api and
+# this is irrelevant.
+CORS_ORIGINS = [
+    origin.strip()
+    for origin in os.environ.get("CORS_ORIGINS", "http://localhost:5173").split(",")
+    if origin.strip()
+]
+
+
+def ensure_dirs() -> None:
+    os.makedirs(PROJECTS_DIR, exist_ok=True)
+
+
+def project_dir(slug: str) -> str:
+    return os.path.join(PROJECTS_DIR, slug)