feat: tiered LLM (GLM free / Claude paid) + rate limits + quota enforcement
All checks were successful
Deploy to Production / deploy (push) Successful in 53s

The free tier was hemorrhaging Anthropic cost with no abuse cap (no rate
limit on /preview, Opus default in the build worker, 5-min cache TTL that
made cache-miss the common case). This switches free users to GLM, paid
users to Claude tiers, and tightens every leak found in the audit.

Backend:
- @bmm/llm: GLM provider via Zhipu's OpenAI-compatible endpoint, pickPreviewModel
  + pickBuildModel helpers, plan-aware ModelChoice
- preview-cache TTL 5min -> 24h (kills the cache-miss path)
- /v1/servers/preview: picks model from caller's plan, returns model name to UI
- /v1/servers POST: enforces SERVER_LIMITS per plan (402), rate-limits builds
- daily rate-limit on preview (5/40/150/1000) and build (3/20/100/500)
- /v1/auth/me returns plan so the wizard can show the right model name
- generator worker: GLM default, Anthropic Sonnet fallback if GLM errors

Frontend:
- Wizard fetches plan, shows "<model> is drafting the tool spec" pre-emptively,
  upgrade hint for hobby users, friendly errors for 402 / 429
- Pricing page: AI-model line per tier (Open-tier / Haiku / Sonnet / Opus),
  Team €149 -> €199, Enterprise €499 -> €999, daily-preview limit per tier
- Privacy + Security: explicit subprocessor disclosure for Anthropic (US) /
  Zhipu (CN) and which tier uses which

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Marco Sadjadi
2026-05-23 23:50:00 +02:00
parent 66128c73d8
commit bc174c1302
14 changed files with 537 additions and 58 deletions

View File

@@ -40,7 +40,11 @@ const PILLARS = [
},
{
title: 'Rate limiting',
body: 'Default 100 requests/min/IP per tool, enforced at the Traefik layer before traffic ever reaches your container.',
body: 'Default 100 requests/min/IP per tool, enforced at the Traefik layer before traffic ever reaches your container. Daily preview + build caps per tier protect against runaway LLM spend.',
},
{
title: 'AI provider by tier — transparent',
body: "Hobby (free) tier uses Zhipu's GLM model (servers in China) for prompt analysis — chosen for cost so we can offer a real free tier. Pro, Team and Enterprise use Anthropic Claude (US). Enterprise can request EU-only data residency. The provider is shown live in the wizard so you always know where your prompt is going.",
},
];