feat: add scientific data and code hosting module

README.md

@@ -1,2 +1,6 @@
 # deepevents.ai
 deepevents.ai main codebase
+
+## Modules
+
+- [`scientific-data-code-hosting`](./scientific-data-code-hosting) - runnable prototype for structured artifact storage, FAIR metadata, dataset versioning, executable environments, and compute triggers.

scientific-data-code-hosting/README.md

@@ -0,0 +1,60 @@
+# Scientific Data & Code Hosting
+
+This module is a self-contained implementation for SCIBASE.AI issue #14. It models structured storage, metadata standards, FAIR compliance, upload versioning, artifact previews, executable environments, and compute triggers for reproducible scientific data/code hosting.
+
+## What It Covers
+
+- Storage manifest for datasets, metadata, code, notebooks, figures, models, and raw instrument output.
+- Folder-based organization for `data/`, `code/`, `results/`, and `raw/`.
+- Metadata-aware previews for CSV tables, notebooks, code, figures, and binary/model artifacts.
+- Upload versioning and dataset diffing.
+- JSON-LD, DataCite, and schema.org-style metadata.
+- FAIR compliance flags for findability, accessibility, interoperability, and reusability.
+- Scientific tagging for keywords, instruments, organisms, and variables.
+- Docker/Kubernetes-style executable environments for Python, R, and Julia stacks.
+- Sandboxed analysis execution and manual/cron compute triggers.
+
+## Run Locally
+
+```bash
+cd scientific-data-code-hosting
+npm test
+npm start
+```
+
+Then open `http://localhost:4133`.
+
+## API Surface
+
+- `GET /api/dashboard`
+- `GET /api/storage/manifest`
+- `GET /api/metadata`
+- `GET /api/execute?environment=env-python`
+
+## Requirement Mapping
+
+- Scalable storage engine: implemented by `buildStorageManifest`.
+- Major file types and folder organization: represented in `artifactStore.folders` and `artifactStore.artifacts`.
+- Metadata-aware previews: implemented by `buildPreview`.
+- Upload versioning and diffing: implemented by `versions` and `diffDatasetVersions`.
+- JSON-LD, DataCite, schema.org, and FAIR: implemented by `buildMetadataBundle`.
+- Tagging system: returned in metadata tags and artifact tags.
+- Executable environments: represented by Docker/Kubernetes environment definitions.
+- Sandboxed execution and compute triggers: implemented by `runExecutableEnvironment` and dashboard trigger metadata.
+
+## Verification
+
+```bash
+npm test
+node src/server.js
+```
+
+Optional smoke checks:
+
+```bash
+curl -s http://localhost:4133/api/dashboard
+curl -s http://localhost:4133/api/storage/manifest
+curl -s "http://localhost:4133/api/execute?environment=env-python"
+```
+
+Demo artifacts are committed under `docs/demo/`, including `dashboard.png` and `scientific-data-code-hosting-demo.mp4`.

scientific-data-code-hosting/docs/demo-script.md

@@ -0,0 +1,6 @@
+# Demo Script
+
+1. Run `npm test` to verify storage manifests, metadata standards, dataset diffs, executable environments, and dashboard payloads.
+2. Run `npm start` and open `http://localhost:4133`.
+3. Confirm the dashboard shows artifact previews, FAIR metadata, dataset version diff, and sandbox execution.
+4. Smoke-test `/api/storage/manifest`, `/api/metadata`, and `/api/execute?environment=env-python`.

scientific-data-code-hosting/package.json

@@ -0,0 +1,14 @@
+{
+  "name": "@scibase/scientific-data-code-hosting",
+  "version": "0.1.0",
+  "private": true,
+  "description": "Self-contained scientific data and code hosting prototype for SCIBASE.AI issue #14.",
+  "type": "module",
+  "scripts": {
+    "start": "node src/server.js",
+    "test": "node --test test/*.test.js"
+  },
+  "engines": {
+    "node": ">=20"
+  }
+}

scientific-data-code-hosting/public/app.js

@@ -0,0 +1,30 @@
+const dashboard = await fetch("/api/dashboard").then((response) => response.json());
+
+document.querySelector("#storage").textContent = `${dashboard.manifest.artifacts.length} artifacts · ${dashboard.manifest.totalBytes} bytes`;
+document.querySelector("#artifacts").innerHTML = dashboard.manifest.artifacts
+  .map((artifact) => `<div class="row"><strong>${artifact.path}</strong><span>${artifact.type} · ${artifact.preview.kind}</span></div>`)
+  .join("");
+
+document.querySelector("#metadata").innerHTML = [
+  row("DOI", dashboard.metadata.dataCite.identifier.identifier),
+  row("Findable", dashboard.metadata.fair.findable),
+  row("Accessible", dashboard.metadata.fair.accessible),
+  row("Reusable", dashboard.metadata.fair.reusable)
+].join("");
+
+document.querySelector("#diff").innerHTML = [
+  row("Added samples", dashboard.versionDiff.addedSamples.join(", ") || "none"),
+  row("Removed samples", dashboard.versionDiff.removedSamples.join(", ") || "none"),
+  row("Row delta", dashboard.versionDiff.rowDelta)
+].join("");
+
+document.querySelector("#execution").innerHTML = [
+  row("Status", dashboard.execution.status),
+  row("Environment", dashboard.execution.environment.name),
+  row("Sandbox", `${dashboard.execution.sandbox.isolation}, network ${dashboard.execution.sandbox.network}`),
+  row("Score", dashboard.execution.reproducibilityScore)
+].join("");
+
+function row(label, value) {
+  return `<div class="row"><span>${label}</span><strong>${String(value)}</strong></div>`;
+}

scientific-data-code-hosting/public/index.html

@@ -0,0 +1,40 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="utf-8" />
+    <meta name="viewport" content="width=device-width, initial-scale=1" />
+    <title>SCIBASE Data & Code Hosting</title>
+    <link rel="stylesheet" href="/styles.css" />
+  </head>
+  <body>
+    <main class="shell">
+      <header>
+        <p>SCIBASE.AI / issue #14</p>
+        <h1>Scientific Data & Code Hosting</h1>
+      </header>
+      <section class="grid">
+        <article class="panel hero">
+          <p class="label">Storage Engine</p>
+          <h2 id="storage">Loading...</h2>
+          <div id="artifacts"></div>
+        </article>
+        <article class="panel">
+          <p class="label">Metadata & FAIR</p>
+          <h2>Standards bundle</h2>
+          <div id="metadata"></div>
+        </article>
+        <article class="panel">
+          <p class="label">Versioning</p>
+          <h2>Dataset diff</h2>
+          <div id="diff"></div>
+        </article>
+        <article class="panel">
+          <p class="label">Executable Environment</p>
+          <h2>Sandbox run</h2>
+          <div id="execution"></div>
+        </article>
+      </section>
+    </main>
+    <script type="module" src="/app.js"></script>
+  </body>
+</html>

scientific-data-code-hosting/public/styles.css

@@ -0,0 +1,110 @@
+:root {
+  --ink: #111715;
+  --muted: #64706b;
+  --line: #d8dfda;
+  --paper: #f3f5ef;
+  --panel: #ffffff;
+  --green: #17664d;
+  --blue: #265f8a;
+}
+
+* {
+  box-sizing: border-box;
+}
+
+body {
+  margin: 0;
+  background: var(--paper);
+  color: var(--ink);
+  font-family: Inter, ui-sans-serif, system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif;
+}
+
+.shell {
+  max-width: 1280px;
+  margin: 0 auto;
+  padding: 32px;
+}
+
+header {
+  display: flex;
+  align-items: end;
+  justify-content: space-between;
+  gap: 24px;
+  margin-bottom: 24px;
+}
+
+p,
+h1,
+h2 {
+  margin: 0;
+}
+
+header p,
+.label {
+  color: var(--muted);
+  font-size: 12px;
+  font-weight: 900;
+  letter-spacing: 0.08em;
+  text-transform: uppercase;
+}
+
+h1 {
+  max-width: 820px;
+  font-size: clamp(38px, 6vw, 76px);
+  line-height: 0.95;
+}
+
+h2 {
+  margin-top: 8px;
+  font-size: 24px;
+}
+
+.grid {
+  display: grid;
+  grid-template-columns: 1.05fr 0.95fr;
+  gap: 16px;
+}
+
+.panel {
+  min-height: 260px;
+  border: 1px solid var(--line);
+  background: var(--panel);
+  padding: 24px;
+}
+
+.hero {
+  grid-row: span 2;
+}
+
+.row {
+  border-top: 1px solid var(--line);
+  padding-top: 12px;
+  margin-top: 14px;
+}
+
+.row span {
+  display: block;
+  color: var(--muted);
+}
+
+.row strong {
+  display: block;
+  color: var(--green);
+  overflow-wrap: anywhere;
+}
+
+.hero .row strong {
+  color: var(--blue);
+}
+
+@media (max-width: 820px) {
+  .shell {
+    padding: 18px;
+  }
+
+  header,
+  .grid {
+    display: grid;
+    grid-template-columns: 1fr;
+  }
+}