AI load shedding: Load Shedding When the Model Is Sick

# ✅ Sliding-window health for the model backend
from collections import deque

class ModelHealth:
    def __init__(self, window=200):
        self.events = deque(maxlen=window)

    def record(self, ok: bool, latency_ms: float) -> None:
        self.events.append((ok, latency_ms))

    def unhealthy(self) -> bool:
        if len(self.events) < 50:
            return False
        err = sum(1 for ok, _ in self.events if not ok) / len(self.events)
        p95 = sorted(l for _, l in self.events)[int(0.95 * len(self.events))]
        return err > 0.08 or p95 > 12_000

// ✅ Typed degradation the client can render
type AiMode = "full" | "read_only" | "draft_only" | "offline";

export function nextMode(h: { errorRate: number; throttled: boolean }): AiMode {
  if (h.errorRate > 0.2 || h.throttled) return "offline";
  if (h.errorRate > 0.08) return "read_only";
  if (h.errorRate > 0.03) return "draft_only";
  return "full";
}