541 B
541 B
5.8 — Rate limiting Tier 3 (atlas) (GREEN)
Phase: 5 — Chat + Rate Limiter (Surface D) Stage: GREEN
Depends on: 5.7
- Global chat semaphore = 6 (2 of 8 GPU slots kept as operator headroom); queue depth 20 then reject
429; per-session budget 12 msg/24h; per-request timeout 120s hard server-side; disconnect cancels upstream immediately (req.Context()threaded to vLLM request)
Verify
# load test at 20 concurrent clients
# GPU sequence usage never exceeds 6, no upstream 5xx, queue drains