feat: F019 AI monitoring layer — output transparency & governance workspace

Full 2-panel workspace at /ops/ai-monitoring: metrics strip (total, failed,
pending, approval rate, top prompt version, active model), filterable output
table by type/status/error, and detail panel with output preview, prompt
versioning, error details, and role-aware review actions.

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

src/provider/IAIMonitoringProvider.ts

@@ -0,0 +1,15 @@
+import type { AIOutput, AIOutputType } from '../domain/aiOutput'
+import type { ReviewStatus } from '../domain/enums'
+
+export interface AIMonitoringFilters {
+  type?: AIOutputType
+  reviewStatus?: ReviewStatus
+  hasError?: boolean
+  model?: string
+}
+
+export interface IAIMonitoringProvider {
+  getOutputs(filters?: AIMonitoringFilters): Promise<AIOutput[]>
+  getOutput(id: string): Promise<AIOutput | null>
+  updateReviewStatus(id: string, status: ReviewStatus): Promise<AIOutput>
+}