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>
2026-04-25 12:42:09 -04:00
parent d7d77238b9
commit 901db02a6b
17 changed files with 1349 additions and 229 deletions
@@ -1,5 +1,6 @@
-import type { GameState, MarketState, BenchmarkResult, Competitor } from '@ai-tycoon/shared';
-import { CONSUMER_TOKENS_PER_SUBSCRIBER } from '@ai-tycoon/shared';
+import type { GameState, MarketState, BenchmarkResult } from '@ai-tycoon/shared';
+import { CONSUMER_TOKENS_PER_SUBSCRIBER, API_TOKENS_PER_DEVELOPER_PER_TICK, BATCH_API_DEMAND_PER_DEV, makeInitialServingMetrics } from '@ai-tycoon/shared';
+import type { TrafficPriority, TierServingMetrics } from '@ai-tycoon/shared';
 import { BENCHMARKS } from '../../data/benchmarks';
 import { computeSeasonal } from './seasonalSystem';
 import { updateObsolescence } from './obsolescenceSystem';
@@ -9,6 +10,9 @@ import { processApiTiers } from './apiTierSystem';
 import { processProductLines } from './productLines';
 import { processDeveloperEcosystem } from './developerEcosystem';
 import { processEnterprisePipeline } from './enterprisePipeline';
+import { processServingPipeline } from './servingPipeline';
+import type { DemandByTier } from './servingPipeline';
+import type { ResearchBonuses } from '../researchBonuses';

 export interface MarketTickResult {
  marketState: MarketState;
@@ -44,24 +48,26 @@ function getSegmentQuality(
  return weightedSum / totalWeight;
 }

-export function processMarketV2(state: GameState, currentTickCapacity: number): MarketTickResult {
+export function processMarketV2(
+  state: GameState,
+  currentTickCapacity: number,
+  effectiveInferenceFlops?: number,
+  researchBonuses?: ResearchBonuses,
+): MarketTickResult {
  const consumerQuality = getSegmentQuality('consumer', state.models.benchmarkResults, state.models.bestDeployedModelScore);
  const enterpriseQuality = getSegmentQuality('enterprise', state.models.benchmarkResults, state.models.bestDeployedModelScore);
  const modelQuality = state.models.benchmarkResults.length > 0
    ? (consumerQuality + enterpriseQuality) / 2
    : state.models.bestDeployedModelScore / 100;

-  // --- Seasonal ---
  const seasonal = computeSeasonal(state.meta.tickCount);

-  // --- Obsolescence ---
  const obsolescence = updateObsolescence(
    state.market.obsolescence,
    state.meta.currentEra,
    state.meta.tickCount,
  );

-  // --- Developer Ecosystem ---
  const freeApiDevs = state.market.apiTiers.tiers.free.developerCount;
  const totalApiDevs = state.market.apiTiers.totalDevelopers;
  const engineeringCount = state.talent.departments.engineering.headcount;
@@ -75,7 +81,6 @@ export function processMarketV2(state: GameState, currentTickCapacity: number):
    state.meta.currentEra,
  );

-  // --- TAM & Market Shares ---
  const chatProduct = state.models.productLines.find(p => p.type === 'chat-product');
  const textApi = state.models.productLines.find(p => p.type === 'text-api');

@@ -106,32 +111,7 @@ export function processMarketV2(state: GameState, currentTickCapacity: number):
  const playerDevCustomers = tam.segments.developer.shares.find(s => s.playerId === 'player')?.customers ?? 0;
  const playerEntCustomers = tam.segments.enterprise.shares.find(s => s.playerId === 'player')?.customers ?? 0;

-  // --- Consumer Tiers ---
-  const consumerDemandEstimate = state.market.consumerTiers.totalUsers * CONSUMER_TOKENS_PER_SUBSCRIBER;
-  const demandCapacityRatio = currentTickCapacity > 0
-    ? consumerDemandEstimate / currentTickCapacity
-    : consumerDemandEstimate > 0 ? 10 : 0;
-
-  const consumerResult = processConsumerTiers(
-    state.market.consumerTiers,
-    playerConsumerCustomers,
-    modelQuality,
-    seasonal.multipliers.consumer,
-    demandCapacityRatio,
-    state.infrastructure.networkLatencyPenalty,
-    state.market.overloadPolicy,
-  );
-
-  // --- API Tiers ---
-  const apiResult = processApiTiers(
-    state.market.apiTiers,
-    playerDevCustomers,
-    modelQuality,
-    seasonal.multipliers.api,
-    devEcosystem,
-  );
-
-  // --- Product Lines ---
+  // --- Product Lines (compute first to get token demand) ---
  const productResult = processProductLines(
    state.market.codeAssistant,
    state.market.agentsPlatform,
@@ -142,22 +122,103 @@ export function processMarketV2(state: GameState, currentTickCapacity: number):
    seasonal.multipliers.enterprise,
  );

-  // --- Enterprise Pipeline ---
+  // --- Pre-compute demand estimates by tier for serving pipeline ---
+  const consumerTiers = state.market.consumerTiers;
+  const apiTiers = state.market.apiTiers;
+  const enterprise = state.market.enterprise;
+
+  const consumerPaidTokens = (consumerTiers.tiers.plus.userCount + consumerTiers.tiers.pro.userCount + consumerTiers.tiers.team.userCount) * CONSUMER_TOKENS_PER_SUBSCRIBER;
+  const consumerFreeTokens = consumerTiers.tiers.free.userCount * CONSUMER_TOKENS_PER_SUBSCRIBER;
+
+  const apiPaidTokens =
+    apiTiers.tiers.payg.developerCount * API_TOKENS_PER_DEVELOPER_PER_TICK.payg
+    + apiTiers.tiers.scale.developerCount * API_TOKENS_PER_DEVELOPER_PER_TICK.scale
+    + apiTiers.tiers['enterprise-api'].developerCount * API_TOKENS_PER_DEVELOPER_PER_TICK['enterprise-api']
+    + productResult.codeAssistantTokenDemand;
+  const apiFreeTokens = apiTiers.tiers.free.developerCount * API_TOKENS_PER_DEVELOPER_PER_TICK.free;
+
+  let enterpriseTokens = 0;
+  for (const contract of enterprise.activeContracts) {
+    enterpriseTokens += contract.tokensPerTick;
+  }
+  enterpriseTokens += productResult.agentsPlatformTokenDemand;
+
+  const demandByTier: DemandByTier = {
+    'enterprise': enterpriseTokens,
+    'api-paid': apiPaidTokens,
+    'consumer-paid': consumerPaidTokens,
+    'api-free': apiFreeTokens,
+    'consumer-free': consumerFreeTokens,
+  };
+
+  // --- Batch API demand ---
+  let batchDemand = 0;
+  if (state.market.overloadPolicy.batchApiEnabled) {
+    for (const id of ['free', 'payg', 'scale', 'enterprise-api'] as const) {
+      batchDemand += apiTiers.tiers[id].developerCount * (BATCH_API_DEMAND_PER_DEV[id] ?? 0);
+    }
+    batchDemand *= Math.max(0.1, modelQuality);
+  }
+
+  const completedResearch = state.research?.completedResearch ?? [];
+
+  // --- Serving Pipeline ---
+  const servingResult = processServingPipeline({
+    modelsState: state.models,
+    effectiveInferenceFlops: effectiveInferenceFlops ?? currentTickCapacity,
+    overloadPolicy: state.market.overloadPolicy,
+    demandByTier,
+    batchApi: {
+      ...state.market.batchApi,
+      totalBatchDemand: batchDemand,
+    },
+    modelQuality,
+    researchUnlocks: {
+      servingRoutingUnlocked: completedResearch.includes('request-routing'),
+      priorityQueuesUnlocked: completedResearch.includes('priority-queues'),
+      batchApiUnlocked: completedResearch.includes('request-batching'),
+      autoScalingBonus: completedResearch.includes('auto-scaling') ? 0.2 : 0,
+    },
+  });
+
+  const sm = servingResult.servingMetrics;
+
+  // --- Consumer Tiers (now with serving metrics) ---
+  const consumerResult = processConsumerTiers(
+    state.market.consumerTiers,
+    playerConsumerCustomers,
+    modelQuality,
+    seasonal.multipliers.consumer,
+    state.infrastructure.networkLatencyPenalty,
+    sm.tierMetrics['consumer-paid'],
+    sm.tierMetrics['consumer-free'],
+  );
+
+  // --- API Tiers (now with serving metrics) ---
+  const apiResult = processApiTiers(
+    state.market.apiTiers,
+    playerDevCustomers,
+    modelQuality,
+    seasonal.multipliers.api,
+    devEcosystem,
+    sm.tierMetrics['api-paid'],
+    sm.tierMetrics['api-free'],
+  );
+
+  // --- Enterprise Pipeline (now with serving metrics) ---
  const salesDept = state.talent.departments.sales;
-  const salesHeadcount = salesDept.headcount;
-  const salesEffectiveness = salesDept.effectiveness;

  const enterpriseResult = processEnterprisePipeline(
    state.market.enterprise,
    state.reputation.score,
    state.models.bestDeployedModelScore,
    state.models.bestDeployedSafetyScore,
-    salesHeadcount,
-    salesEffectiveness,
+    salesDept.headcount,
+    salesDept.effectiveness,
    devEcosystem,
    seasonal.multipliers.enterprise,
    state.meta.tickCount,
-    demandCapacityRatio,
+    sm.tierMetrics['enterprise'],
  );

  // --- Aggregate revenue ---
@@ -165,9 +226,10 @@ export function processMarketV2(state: GameState, currentTickCapacity: number):
    + productResult.codeAssistantRevenue
    + productResult.agentsPlatformRevenue;

-  const apiRevenue = apiResult.apiRevenue
+  let apiRevenue = apiResult.apiRevenue
    + enterpriseResult.contractRevenue
-    - enterpriseResult.slaPenalties;
+    - enterpriseResult.slaPenalties
+    + servingResult.batchRevenue;

  const totalTokenDemand = consumerResult.totalConsumerTokenDemand
    + apiResult.totalApiTokenDemand
@@ -186,26 +248,7 @@ export function processMarketV2(state: GameState, currentTickCapacity: number):
  const openSourceCount = state.market.openSourcedModels.length;
  if (openSourceCount > 0) {
    const revenueReduction = openSourceCount * 0.10 * 0.3;
-    const adjustedApiRevenue = apiRevenue * (1 - revenueReduction);
-    return {
-      marketState: {
-        ...state.market,
-        tam,
-        consumerTiers: consumerResult.consumerTiers,
-        apiTiers: apiResult.apiTiers,
-        codeAssistant: productResult.codeAssistant,
-        agentsPlatform: productResult.agentsPlatform,
-        enterprise: enterpriseResult.enterprise,
-        developerEcosystem: devEcosystem,
-        seasonalPhase: seasonal.phase,
-        seasonalMultiplier: seasonal.multipliers.consumer,
-        obsolescence,
-        subscriberHistory,
-      },
-      apiRevenue: Math.max(0, adjustedApiRevenue),
-      subscriptionRevenue,
-      totalTokenDemand,
-    };
+    apiRevenue = apiRevenue * (1 - revenueReduction);
  }

  return {
@@ -221,6 +264,8 @@ export function processMarketV2(state: GameState, currentTickCapacity: number):
      seasonalPhase: seasonal.phase,
      seasonalMultiplier: seasonal.multipliers.consumer,
      obsolescence,
+      servingMetrics: sm,
+      batchApi: servingResult.batchApi,
      subscriberHistory,
    },
    apiRevenue: Math.max(0, apiRevenue),