Replace decorative overload policy with real serving pipeline and dedicated Serving page

The old overload policy had dead controls (maxQueueDepth, rateLimitPerCustomer never read)
and trivial flat penalties. This replaces it with a full serving pipeline where deployed
models form a fleet, requests route through priority/degradation logic, and policy choices
create meaningful strategic tradeoffs.

New serving pipeline: fleet building from deployed models (size/quant/MoE multipliers),
demand categorization by 5 priority tiers, enterprise capacity reservation, priority-ordered
serving with overflow behaviors (queue/reject/degrade), auto-degradation to faster models
under load, and Batch API to fill idle capacity at discounted rates.

4 new research nodes gate features progressively: Intelligent Request Routing, Priority
Queue System, Request Batching, and Auto-Scaling. New dedicated Serving page with pipeline
metrics, model fleet utilization, and research-gated policy controls.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

packages/shared/src/constants/gameBalance.ts

@@ -118,6 +118,34 @@ export const FLOPS_TO_TOKENS_MULTIPLIER = 26;
 
 export const OVERLOAD_PENALTY_EXPONENT = 1.5;
 
+// --- Serving Pipeline ---
+
+export const REJECTION_SATISFACTION_PENALTY = 0.15;
+export const QUEUE_SATISFACTION_PENALTY = 0.05;
+export const DEGRADATION_SATISFACTION_PENALTY = 0.08;
+
+export const REJECTION_CHURN_MULTIPLIER = 3.0;
+export const QUEUE_CHURN_MULTIPLIER = 1.5;
+
+export const ENTERPRISE_REJECTION_SLA_MULTIPLIER = 3.0;
+
+export const FREE_TIER_REJECTION_TOLERANCE = 0.3;
+export const PAID_TIER_REJECTION_TOLERANCE = 0.05;
+
+export const MODEL_SIZE_THROUGHPUT_SCALER: Record<SizeTier, number> = {
+  nano: 10.0, small: 5.0, medium: 2.0, large: 1.2, flagship: 1.0,
+};
+
+export const BATCH_API_DEMAND_PER_DEV: Record<ApiTierId, number> = {
+  free: 0, payg: 2, scale: 20, 'enterprise-api': 100,
+};
+export const BATCH_API_DEFAULT_DISCOUNT = 0.5;
+export const BATCH_API_MAX_PENDING = 100_000;
+
+export const BATCHING_THROUGHPUT_FACTOR = 0.15;
+export const BASE_LATENCY_MS = 50;
+export const QUEUE_LATENCY_MS_PER_PERCENT = 5;
+
 export const ERA_THRESHOLDS = {
   scaleup: { revenue: 10_000, capability: 15, reputation: 30 },
   bigtech: { revenue: 1_000_000, capability: 50, reputation: 60 },

packages/shared/src/types/gameState.ts

@@ -52,4 +52,4 @@ export const INITIAL_SETTINGS: GameSettings = {
   musicVolume: 0.5,
 };
 
-export const SAVE_VERSION = 8;
+export const SAVE_VERSION = 9;

packages/shared/src/types/market.ts

@@ -170,13 +170,93 @@ export interface ObsolescenceState {
   newModelBoostRemaining: number;
 }
 
-// --- Overload Policy (kept from original) ---
+// --- Serving Pipeline & Overload Policy ---
+
+export type TrafficPriority = 'enterprise' | 'api-paid' | 'consumer-paid' | 'api-free' | 'consumer-free';
+export type RoutingStrategy = 'quality-first' | 'speed-first' | 'balanced';
+export type OverflowBehavior = 'queue' | 'reject' | 'degrade';
+
+export const TRAFFIC_PRIORITIES: TrafficPriority[] = ['enterprise', 'api-paid', 'consumer-paid', 'api-free', 'consumer-free'];
 
 export interface OverloadPolicy {
+  priorityOrder: TrafficPriority[];
+  overflowBehavior: Record<TrafficPriority, OverflowBehavior>;
   maxQueueDepth: number;
-  rateLimitPerCustomer: number;
-  degradeQualityUnderLoad: boolean;
-  prioritizeEnterprise: boolean;
+  rateLimitPerCustomer: Record<TrafficPriority, number>;
+  enterpriseReservation: number;
+  routingStrategy: RoutingStrategy;
+  autoDegradation: {
+    enabled: boolean;
+    triggerThreshold: number;
+    minQualityFloor: number;
+  };
+  batchApiEnabled: boolean;
+  batchApiDiscount: number;
+  batchApiMaxDelay: number;
+}
+
+export interface TierServingMetrics {
+  demandTokens: number;
+  servedTokens: number;
+  queuedTokens: number;
+  rejectedTokens: number;
+  degradedTokens: number;
+  avgQualityDelivered: number;
+}
+
+export interface ModelUtilizationEntry {
+  modelId: string;
+  modelName: string;
+  quantization: string | null;
+  qualityScore: number;
+  throughputCapacity: number;
+  throughputUsed: number;
+  utilization: number;
+}
+
+export interface ServingMetrics {
+  tierMetrics: Record<TrafficPriority, TierServingMetrics>;
+  totalServed: number;
+  totalQueued: number;
+  totalRejected: number;
+  totalDegraded: number;
+  effectiveQuality: number;
+  avgLatencyMs: number;
+  modelUtilization: ModelUtilizationEntry[];
+  batchApiTokensServed: number;
+  batchApiRevenue: number;
+}
+
+export interface BatchApiState {
+  totalBatchDemand: number;
+  pendingQueue: number;
+  servedLastTick: number;
+  revenue: number;
+}
+
+function makeEmptyTierMetrics(): TierServingMetrics {
+  return { demandTokens: 0, servedTokens: 0, queuedTokens: 0, rejectedTokens: 0, degradedTokens: 0, avgQualityDelivered: 1 };
+}
+
+export function makeInitialServingMetrics(): ServingMetrics {
+  return {
+    tierMetrics: {
+      'enterprise': makeEmptyTierMetrics(),
+      'api-paid': makeEmptyTierMetrics(),
+      'consumer-paid': makeEmptyTierMetrics(),
+      'api-free': makeEmptyTierMetrics(),
+      'consumer-free': makeEmptyTierMetrics(),
+    },
+    totalServed: 0,
+    totalQueued: 0,
+    totalRejected: 0,
+    totalDegraded: 0,
+    effectiveQuality: 1,
+    avgLatencyMs: 0,
+    modelUtilization: [],
+    batchApiTokensServed: 0,
+    batchApiRevenue: 0,
+  };
 }
 
 // --- Root Market State ---
@@ -193,6 +273,8 @@ export interface MarketState {
   seasonalMultiplier: number;
   obsolescence: ObsolescenceState;
   overloadPolicy: OverloadPolicy;
+  servingMetrics: ServingMetrics;
+  batchApi: BatchApiState;
   openSourcedModels: string[];
   subscriberHistory: { tick: number; subscribers: number }[];
 }
@@ -315,10 +397,39 @@ export const INITIAL_MARKET: MarketState = {
     newModelBoostRemaining: 0,
   },
   overloadPolicy: {
+    priorityOrder: ['enterprise', 'api-paid', 'consumer-paid', 'api-free', 'consumer-free'],
+    overflowBehavior: {
+      'enterprise': 'queue' as OverflowBehavior,
+      'api-paid': 'queue' as OverflowBehavior,
+      'consumer-paid': 'degrade' as OverflowBehavior,
+      'api-free': 'reject' as OverflowBehavior,
+      'consumer-free': 'reject' as OverflowBehavior,
+    },
     maxQueueDepth: 100,
-    rateLimitPerCustomer: 1000,
-    degradeQualityUnderLoad: false,
-    prioritizeEnterprise: true,
+    rateLimitPerCustomer: {
+      'enterprise': 10000,
+      'api-paid': 1000,
+      'consumer-paid': 500,
+      'api-free': 100,
+      'consumer-free': 50,
+    },
+    enterpriseReservation: 0.2,
+    routingStrategy: 'balanced' as RoutingStrategy,
+    autoDegradation: {
+      enabled: true,
+      triggerThreshold: 0.85,
+      minQualityFloor: 0.75,
+    },
+    batchApiEnabled: false,
+    batchApiDiscount: 0.5,
+    batchApiMaxDelay: 60,
+  },
+  servingMetrics: makeInitialServingMetrics(),
+  batchApi: {
+    totalBatchDemand: 0,
+    pendingQueue: 0,
+    servedLastTick: 0,
+    revenue: 0,
   },
   openSourcedModels: [],
   subscriberHistory: [],