feat: add shadow AI benchmarking for admin model comparison

Add a new admin-only feature that allows the platform owner to benchmark
the production AI model against up to 2 alternate models (any OpenAI-compatible
API) using real tenant data, without impacting users.

Backend:
- Shared AI caller utility (ai-caller.ts) for OpenAI-compatible endpoints
- Shadow AI module with service, controller, and 3 entities
- 6 admin API endpoints for model config CRUD, run trigger, and history
- Auto-creates shadow_ai_models, shadow_runs, shadow_run_results tables
- Exposes health-scores and investment-planning prompt builders for reuse

Frontend:
- New admin page at /admin/shadow-ai with 3 tabs:
  - Model Configuration (production + 2 alternate slots)
  - Run Comparison (tenant select, feature select, side-by-side results)
  - History (filterable run log with detail drill-down)
- Full side-by-side output display with diff highlighting
- Sidebar navigation link for AI Benchmarking

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

backend/src/modules/shadow-ai/entities/shadow-run-result.entity.ts

@@ -0,0 +1,52 @@
+import {
+  Entity,
+  PrimaryGeneratedColumn,
+  Column,
+  CreateDateColumn,
+  ManyToOne,
+  JoinColumn,
+} from 'typeorm';
+import { ShadowRun } from './shadow-run.entity';
+
+@Entity({ schema: 'shared', name: 'shadow_run_results' })
+export class ShadowRunResult {
+  @PrimaryGeneratedColumn('uuid')
+  id: string;
+
+  @Column({ name: 'run_id', type: 'uuid' })
+  runId: string;
+
+  @Column({ name: 'model_role', type: 'varchar', length: 20 })
+  modelRole: string;
+
+  @Column({ name: 'model_name', type: 'varchar', length: 200 })
+  modelName: string;
+
+  @Column({ name: 'api_url', type: 'varchar', length: 500 })
+  apiUrl: string;
+
+  @Column({ name: 'raw_response', type: 'text', nullable: true })
+  rawResponse: string;
+
+  @Column({ name: 'parsed_response', type: 'jsonb', nullable: true })
+  parsedResponse: any;
+
+  @Column({ name: 'response_time_ms', type: 'integer', nullable: true })
+  responseTimeMs: number;
+
+  @Column({ name: 'token_usage', type: 'jsonb', nullable: true })
+  tokenUsage: any;
+
+  @Column({ type: 'varchar', length: 20, default: 'pending' })
+  status: string;
+
+  @Column({ name: 'error_message', type: 'text', nullable: true })
+  errorMessage: string;
+
+  @CreateDateColumn({ name: 'created_at', type: 'timestamptz' })
+  createdAt: Date;
+
+  @ManyToOne(() => ShadowRun, (run) => run.results, { onDelete: 'CASCADE' })
+  @JoinColumn({ name: 'run_id' })
+  run: ShadowRun;
+}