Automate the evaluation on a weekly schedule
Deploy to Cloudflare Pages / deploy (push) Successful in 30s

- scripts/sync-catalog.mjs: rebuilds the Go catalogue from models.dev and benchmark
  scores from Artificial Analysis, and records what changed in snapshot.json
- scripts/build-models-md.mjs: regenerates MODELS.md from the data layers
- scripts/notify-new-models.mjs: files an issue when a new model needs a write-up
- weekly-eval.yml: cron every Monday 05:23 UTC -> refresh -> commit -> Pages deploy
- site now renders every model in the catalogue (33) with a data-snapshot stamp;
  auto-added models are flagged 'no write-up' until described
- replaced scripts/refresh-evals.mjs with the wider sync script
This commit is contained in:
2026-10-21 17:06:51 +00:00
parent e76281876b
commit 4e5a13f7b6
13 changed files with 2934 additions and 610 deletions
+5 -1
View File
@@ -6,9 +6,13 @@
"type": "module",
"scripts": {
"dev": "wrangler pages dev site --port 8788",
"sync": "node scripts/sync-catalog.mjs",
"build:md": "node scripts/build-models-md.mjs",
"notify": "node scripts/notify-new-models.mjs",
"refresh": "npm run sync && npm run build:md && npm run notify",
"deploy": "./scripts/deploy.sh",
"deploy:pages": "wrangler pages deploy site --project-name opencodogoevals --branch main",
"project:create": "wrangler pages project create opencodogoevals"
"project:create": "wrangler pages project create opencodogoevals --production-branch main"
},
"devDependencies": {
"wrangler": "^4.0.0"