Become the data-only repo: site and worker move to private nagi-bench-site

The showcase app and the arena backend now live in the private
nagi-bench-site repo and deploy to Cloudflare Pages, fetching this
repo's models/, outputs/ and cases.json at build time. CI here is a
standalone data validation (same rules as before, no build), plus an
optional repository_dispatch that triggers an instant site rebuild when
SITE_DISPATCH_TOKEN is configured — otherwise the site's 6-hour cron
picks new data up.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

scripts/validate-data.ts

@@ -0,0 +1,110 @@
+// Validates the contribution data: models/<model-id>.json registrations and
+// their artifacts under outputs/. Runs in CI for every PR and push, so a
+// malformed or undocumented contribution fails before it can ship.
+import { existsSync, readFileSync, readdirSync } from 'node:fs'
+import { dirname, join } from 'node:path'
+import { fileURLToPath } from 'node:url'
+
+const root = join(dirname(fileURLToPath(import.meta.url)), '..')
+const modelsDir = join(root, 'models')
+const outputsDir = join(root, 'outputs')
+
+const cases = JSON.parse(readFileSync(join(root, 'cases.json'), 'utf8')) as Array<{
+  id: string
+  kind: string
+}>
+const caseKind = new Map(cases.map((c) => [c.id, c.kind]))
+
+const ID_RE = /^[a-z0-9]+(-[a-z0-9]+)*$/
+const errors: string[] = []
+
+const isBilingual = (v: unknown): boolean => {
+  if (!v || typeof v !== 'object') return false
+  const { zh, en } = v as { zh?: unknown; en?: unknown }
+  return typeof zh === 'string' && zh.trim() !== '' && typeof en === 'string' && en.trim() !== ''
+}
+
+const modelIds = new Set<string>()
+for (const f of readdirSync(modelsDir).filter((f) => f.endsWith('.json'))) {
+  const id = f.replace(/\.json$/, '')
+  modelIds.add(id)
+  if (!ID_RE.test(id)) {
+    errors.push(`models/${f}: id "${id}" must be lowercase letters/digits/dashes only (it doubles as the outputs/ folder name)`)
+  }
+
+  type RunJson = { note?: unknown; file?: unknown; contributor?: unknown }
+  let def: { label?: unknown; vendor?: unknown; order?: unknown; runs?: Record<string, RunJson | RunJson[]> }
+  try {
+    def = JSON.parse(readFileSync(join(modelsDir, f), 'utf8'))
+  } catch (e) {
+    errors.push(`models/${f}: invalid JSON (${e})`)
+    continue
+  }
+
+  if (typeof def.label !== 'string' || !def.label.trim()) errors.push(`models/${f}: "label" is required`)
+  if (typeof def.vendor !== 'string' || !def.vendor.trim()) errors.push(`models/${f}: "vendor" is required`)
+  if (def.order !== undefined && typeof def.order !== 'number') errors.push(`models/${f}: "order" must be a number`)
+
+  for (const [caseId, runRaw] of Object.entries(def.runs ?? {})) {
+    if (!caseKind.has(caseId)) {
+      errors.push(`models/${f}: unknown case "${caseId}" (known: ${[...caseKind.keys()].join(', ')})`)
+      continue
+    }
+    const variants = Array.isArray(runRaw) ? runRaw : [runRaw]
+    if (!variants.length) errors.push(`models/${f}: runs.${caseId} is an empty array`)
+    const seenFiles = new Set<string>()
+    variants.forEach((run, i) => {
+      const where = variants.length > 1 ? `runs.${caseId}[${i}]` : `runs.${caseId}`
+      if (!isBilingual(run?.note)) {
+        errors.push(`models/${f}: ${where} needs a bilingual "note" ({ "zh", "en" }) documenting provenance (tool, effort level, one-shot or fixed)`)
+      }
+      if (run?.file !== undefined && typeof run.file !== 'string') {
+        errors.push(`models/${f}: ${where}.file must be a string`)
+      }
+      if (run?.contributor !== undefined && (typeof run.contributor !== 'string' || !run.contributor.trim())) {
+        errors.push(`models/${f}: ${where}.contributor must be a non-empty GitHub username`)
+      }
+      const file = (typeof run?.file === 'string' && run.file) || `${caseId}.${caseKind.get(caseId)}`
+      if (seenFiles.has(file)) {
+        errors.push(`models/${f}: ${where} resolves to the same artifact "${file}" as another variant — extra variants must set a distinct "file"`)
+      }
+      seenFiles.add(file)
+      if (!existsSync(join(outputsDir, id, file))) {
+        errors.push(`models/${f}: ${where} declared but artifact missing: outputs/${id}/${file}`)
+      }
+    })
+  }
+}
+
+for (const entry of readdirSync(outputsDir, { withFileTypes: true })) {
+  if (entry.isDirectory() && !modelIds.has(entry.name)) {
+    errors.push(`outputs/${entry.name}/ exists but models/${entry.name}.json is missing`)
+  }
+}
+
+// Every file under outputs/<id>/ must be declared by a run — loose artifacts
+// would otherwise ship without provenance.
+for (const id of modelIds) {
+  const dir = join(outputsDir, id)
+  if (!existsSync(dir)) continue
+  const def = JSON.parse(readFileSync(join(modelsDir, `${id}.json`), 'utf8')) as {
+    runs?: Record<string, { file?: string } | Array<{ file?: string }>>
+  }
+  const declared = new Set<string>()
+  for (const [caseId, runRaw] of Object.entries(def.runs ?? {})) {
+    for (const run of Array.isArray(runRaw) ? runRaw : [runRaw]) {
+      declared.add(run?.file ?? `${caseId}.${caseKind.get(caseId)}`)
+    }
+  }
+  for (const file of readdirSync(dir)) {
+    if (!declared.has(file)) {
+      errors.push(`outputs/${id}/${file} is not declared by any run in models/${id}.json`)
+    }
+  }
+}
+
+if (errors.length) {
+  console.error(`Data validation failed (${errors.length}):\n- ${errors.join('\n- ')}`)
+  process.exit(1)
+}
+console.log(`Data OK: ${modelIds.size} models, ${caseKind.size} cases validated`)