frontend/src/api/index.ts

@@ -294,4 +294,27 @@ export interface SystemHealth {
   sessions: { active: number; max: number };
 }
 
+export type ModelRole = 'main_llm' | 'hyde_llm' | 'embedding' | 'reranker';
+export type ModelStatus = 'ok' | 'error' | 'never_called' | 'disabled';
+
+export interface ModelUsageEntry {
+  role: ModelRole;
+  role_label: string;
+  provider: string;
+  model: string;
+  enabled: boolean;
+  status: ModelStatus;
+  total_tokens: number;
+  call_count_ok: number;
+  call_count_error: number;
+  last_called_at: string | null;
+  last_latency_ms: number | null;
+  last_error: string | null;
+  shares_usage_with: ModelRole | null;
+}
+
+export interface ModelUsageResponse {
+  models: ModelUsageEntry[];
+}
+
 export { API_BASE_URL };

frontend/src/api/status.ts

@@ -1,4 +1,4 @@
-import { fetchAPI, type SystemConfig, type SystemHealth, type SystemStats } from './index';
+import { fetchAPI, type ModelUsageResponse, type SystemConfig, type SystemHealth, type SystemStats } from './index';
 
 export async function getSystemStats(): Promise<SystemStats> {
   return fetchAPI<SystemStats>('/status/stats');
@@ -12,4 +12,14 @@ export async function getSystemHealth(): Promise<SystemHealth> {
   return fetchAPI<SystemHealth>('/status/health');
 }
 
-export type { SystemConfig, SystemHealth, SystemStats };
+/** Passive read: current connection status + cumulative token usage for all 4 AI model roles. */
+export async function getModelUsage(): Promise<ModelUsageResponse> {
+  return fetchAPI<ModelUsageResponse>('/status/models');
+}
+
+/** Active check: sends one minimal request to each enabled model, then returns fresh statuses. */
+export async function pingModelConnections(): Promise<ModelUsageResponse> {
+  return fetchAPI<ModelUsageResponse>('/status/models/ping', { method: 'POST' });
+}
+
+export type { ModelUsageResponse, SystemConfig, SystemHealth, SystemStats };