feat(ai-runtime): complete ai runtime policy refactor (ADR-035)

frontend/app/(admin)/admin/ai/page.tsx

@@ -56,9 +56,16 @@ function normalizeLoadedModels(value: unknown): VramLoadedModelView[] {
   }
   return value.map((item, index) => {
     if (typeof item === 'string') {
+      const name = item.toLowerCase();
+      let normName = item;
+      if (name.includes('ocr') || name.includes('typhoon-np-dms-ocr')) {
+        normName = 'np-dms-ocr';
+      } else if (name.includes('typhoon') || name.includes('np-dms-ai')) {
+        normName = 'np-dms-ai';
+      }
       return {
         modelId: `${item}-${index}`,
-        modelName: item,
+        modelName: normName,
       };
     }
     if (item && typeof item === 'object') {
@@ -68,10 +75,17 @@ function normalizeLoadedModels(value: unknown): VramLoadedModelView[] {
         name?: string;
         vramUsageMB?: number;
       };
-      const modelName = model.modelName ?? model.name ?? `model-${index + 1}`;
+      const rawName = model.modelName ?? model.name ?? `model-${index + 1}`;
+      const name = rawName.toLowerCase();
+      let normName = rawName;
+      if (name.includes('ocr') || name.includes('typhoon-np-dms-ocr')) {
+        normName = 'np-dms-ocr';
+      } else if (name.includes('typhoon') || name.includes('np-dms-ai')) {
+        normName = 'np-dms-ai';
+      }
       return {
-        modelId: model.modelId ?? modelName,
-        modelName,
+        modelId: model.modelId ?? rawName,
+        modelName: normName,
         vramUsageMB: model.vramUsageMB,
       };
     }
@@ -122,7 +136,13 @@ export default function AiAdminConsolePage() {
       return res as SandboxProject[];
     },
   });
-  const healthOllamaModels = ensureArray<string>(health?.ollama?.models);
+  const rawHealthOllamaModels = ensureArray<string>(health?.ollama?.models);
+  const healthOllamaModels = Array.from(new Set(rawHealthOllamaModels.map((m) => {
+    const name = m.toLowerCase();
+    if (name.includes('ocr') || name.includes('typhoon-np-dms-ocr')) return 'np-dms-ocr';
+    if (name.includes('typhoon') || name.includes('np-dms-ai')) return 'np-dms-ai';
+    return m;
+  })));
   const healthQdrantCollections = ensureArray<string>(health?.qdrant?.collections);
   const vramLoadedModels = normalizeLoadedModels(vramStatus?.loadedModels);
   const sandboxProjects = ensureArray<SandboxProject>(projects);

frontend/components/admin/ai/OcrSandboxPromptManager.tsx

@@ -592,7 +592,7 @@ export default function OcrSandboxPromptManager() {
                   </CardTitle>
                   <Badge variant="outline" className="text-xs">
                     {ocrResult.engineUsed === 'typhoon-np-dms-ocr'
-                      ? 'Typhoon OCR'
+                      ? 'np-dms-ocr'
                       : ocrResult.ocrUsed
                         ? 'Tesseract'
                         : 'Fast Path (Text Layer)'}
@@ -601,7 +601,7 @@ export default function OcrSandboxPromptManager() {
                 <CardContent className="pt-4">
                   {ocrResult.fallbackUsed && (
                     <div className="mb-3 rounded-md border border-amber-500/20 bg-amber-500/5 px-3 py-2 text-xs text-amber-600 dark:text-amber-400">
-                      Typhoon OCR unavailable. Fallback to Tesseract was used for this run.
+                      np-dms-ocr unavailable. Fallback to Tesseract was used for this run.
                     </div>
                   )}
                   <div className="relative rounded-md bg-muted p-4 font-mono text-xs overflow-auto max-h-[200px] border border-border/10">

frontend/lib/services/admin-ai.service.ts

@@ -15,6 +15,7 @@
 // - 2026-06-02: normalize VRAM response ให้รองรับ field names จาก backend ปัจจุบันและรูปแบบ loadedModels แบบเดิม
 
 import api from '../api/client';
+import { AiJobResponse } from '../../types/ai';
 
 export interface AiAdminSettings {
   aiFeaturesEnabled: boolean;
@@ -315,6 +316,23 @@ export const adminAiService = {
     const { data } = await api.post(`/ai/ocr-engines/${encodeURIComponent(engineId)}/select`, {});
     return extractData<{ activeEngineName: string }>(data);
   },
+
+  submitAiJob: async (
+    type: string,
+    documentPublicId?: string,
+    attachmentPublicId?: string,
+    payload?: Record<string, unknown>,
+    projectPublicId?: string
+  ): Promise<AiJobResponse> => {
+    const { data } = await api.post('/ai/jobs', {
+      type,
+      documentPublicId,
+      attachmentPublicId,
+      payload,
+      projectPublicId,
+    });
+    return extractData<AiJobResponse>(data);
+  },
 };
 
 export interface OcrEngineResponse {

frontend/public/locales/en/ai.json

@@ -44,5 +44,14 @@
     "delete_confirm": "Delete this pattern?",
     "loading": "Loading...",
     "not_found": "Intent not found"
+  },
+  "ai_runtime_policy": {
+    "error_model_key_forbidden": "model.key is not allowed. The system selects the model automatically.",
+    "error_execution_profile_forbidden": "executionProfile is not allowed in the request payload.",
+    "error_temperature_forbidden": "temperature override is not allowed. Runtime parameters are managed by policy.",
+    "error_top_p_forbidden": "top_p override is not allowed. Runtime parameters are managed by policy.",
+    "error_max_tokens_forbidden": "maxTokens override is not allowed. Runtime parameters are managed by policy.",
+    "error_cpu_timeout": "Retrieval operation timed out on CPU fallback. Please retry later.",
+    "error_large_context_unauthorized": "The large-context profile requires administrator privileges."
   }
 }

frontend/public/locales/th/ai.json

@@ -76,6 +76,14 @@
     "processing": "กำลังประมวลผลด้วย Typhoon LLM...",
     "error_vram": "VRAM ไม่เพียงพอสำหรับโหลดโมเดล Typhoon LLM",
     "error_timeout": "หมดเวลาการประมวลผล LLM (120 วินาที)"
+  },
+  "ai_runtime_policy": {
+    "error_model_key_forbidden": "ไม่อนุญาตให้ระบุ model.key ระบบจะเลือกโมเดลให้อัตโนมัติ",
+    "error_execution_profile_forbidden": "ไม่อนุญาตให้ระบุ executionProfile ใน payload",
+    "error_temperature_forbidden": "ไม่อนุญาตให้ override ค่า temperature พารามิเตอร์ถูกควบคุมโดย Runtime Policy",
+    "error_top_p_forbidden": "ไม่อนุญาตให้ override ค่า top_p พารามิเตอร์ถูกควบคุมโดย Runtime Policy",
+    "error_max_tokens_forbidden": "ไม่อนุญาตให้ override ค่า maxTokens พารามิเตอร์ถูกควบคุมโดย Runtime Policy",
+    "error_cpu_timeout": "การดึงข้อมูลหมดเวลาขณะใช้ CPU fallback กรุณาลองใหม่อีกครั้ง",
+    "error_large_context_unauthorized": "Profile large-context ต้องการสิทธิ์ผู้ดูแลระบบ"
   }
 }
-

frontend/types/ai.ts

@@ -74,3 +74,13 @@ export interface AiPaginatedResult<T> {
   limit: number;
   totalPages: number;
 }
+
+export type ExecutionProfile = 'interactive' | 'standard' | 'quality' | 'deep-analysis';
+
+export interface AiJobResponse {
+  jobId: string;
+  status: 'queued' | 'completed' | 'failed';
+  modelUsed: 'np-dms-ai' | 'np-dms-ocr';
+  effectiveProfile: ExecutionProfile;
+  queueName: 'ai-realtime' | 'ai-batch';
+}