feat: Model/Router server architecture WIP

tools/server/webui/src/app.d.ts

@@ -12,9 +12,20 @@ import type {
 	ApiContextSizeError,
 	ApiErrorResponse,
 	ApiLlamaCppServerProps,
-	ApiProcessingState
+	ApiProcessingState,
+	ApiRouterModelMeta,
+	ApiRouterModelsLoadRequest,
+	ApiRouterModelsLoadResponse,
+	ApiRouterModelsStatusRequest,
+	ApiRouterModelsStatusResponse,
+	ApiRouterModelsListResponse,
+	ApiRouterModelsUnloadRequest,
+	ApiRouterModelsUnloadResponse
 } from '$lib/types/api';
 
+import { ServerMode } from '$lib/enums/server';
+import { ServerModelStatus } from '$lib/enums/model';
+
 import type {
 	ChatMessageType,
 	ChatRole,
@@ -60,6 +71,16 @@ declare global {
 		ApiErrorResponse,
 		ApiLlamaCppServerProps,
 		ApiProcessingState,
+		ApiRouterModelMeta,
+		ApiRouterModelsLoadRequest,
+		ApiRouterModelsLoadResponse,
+		ApiRouterModelsStatusRequest,
+		ApiRouterModelsStatusResponse,
+		ApiRouterModelsListResponse,
+		ApiRouterModelsUnloadRequest,
+		ApiRouterModelsUnloadResponse,
+		ServerMode,
+		ServerModelStatus,
 		ChatMessageData,
 		ChatMessagePromptProgress,
 		ChatMessageSiblingInfo,

tools/server/webui/src/lib/enums/model.ts

@@ -0,0 +1,9 @@
+/**
+ * Model status enum - matches tools/server/server-models.h from C++ server
+ */
+export enum ServerModelStatus {
+	UNLOADED = 'UNLOADED',
+	LOADING = 'LOADING',
+	LOADED = 'LOADED',
+	FAILED = 'FAILED'
+}

tools/server/webui/src/lib/enums/server.ts

@@ -0,0 +1,9 @@
+/**
+ * Server mode enum - used for single/multi-model mode
+ */
+export enum ServerMode {
+	/** Single model mode - server running with a specific model loaded */
+	MODEL = 'MODEL',
+	/** Router mode - server managing multiple model instances */
+	ROUTER = 'ROUTER'
+}

tools/server/webui/src/lib/stores/server.svelte.ts

@@ -2,6 +2,8 @@ import { browser } from '$app/environment';
 import { SERVER_PROPS_LOCALSTORAGE_KEY } from '$lib/constants/localstorage-keys';
 import { ChatService } from '$lib/services/chat';
 import { config } from '$lib/stores/settings.svelte';
+import { ServerMode } from '$lib/enums/server';
+import { updateConfig } from '$lib/stores/settings.svelte';
 
 /**
  * ServerStore - Server state management and capability detection
@@ -52,6 +54,10 @@ class ServerStore {
 	private _error = $state<string | null>(null);
 	private _serverWarning = $state<string | null>(null);
 	private _slotsEndpointAvailable = $state<boolean | null>(null);
+	private _serverMode = $state<ServerMode | null>(null);
+	private _selectedModel = $state<string | null>(null);
+	private _availableModels = $state<ApiRouterModelMeta[]>([]);
+	private _modelLoadingStates = $state<Map<string, boolean>>(new Map());
 	private fetchServerPropsPromise: Promise<void> | null = null;
 
 	private readCachedServerProps(): ApiLlamaCppServerProps | null {
@@ -135,6 +141,48 @@ class ServerStore {
 		return this._serverProps?.default_generation_settings?.params || null;
 	}
 
+	/**
+	 * Get current server mode
+	 */
+	get serverMode(): ServerMode | null {
+		return this._serverMode;
+	}
+
+	/**
+	 * Detect if server is running in router mode (multi-model management)
+	 */
+	get isRouterMode(): boolean {
+		return this._serverMode === ServerMode.ROUTER;
+	}
+
+	/**
+	 * Detect if server is running in model mode (single model loaded)
+	 */
+	get isModelMode(): boolean {
+		return this._serverMode === ServerMode.MODEL;
+	}
+
+	/**
+	 * Get currently selected model in router mode
+	 */
+	get selectedModel(): string | null {
+		return this._selectedModel;
+	}
+
+	/**
+	 * Get list of available models
+	 */
+	get availableModels(): ApiRouterModelMeta[] {
+		return this._availableModels;
+	}
+
+	/**
+	 * Check if a specific model is currently loading
+	 */
+	isModelLoading(modelName: string): boolean {
+		return this._modelLoadingStates.get(modelName) ?? false;
+	}
+
 	/**
 	 * Check if slots endpoint is available based on server properties and endpoint support
 	 */
@@ -198,6 +246,21 @@ class ServerStore {
 				this.persistServerProps(props);
 				this._error = null;
 				this._serverWarning = null;
+
+				// Detect server mode based on model_path
+				if (props.model_path === 'none') {
+					this._serverMode = ServerMode.ROUTER;
+					console.info('Server running in ROUTER mode (multi-model management)');
+
+					// Auto-enable model selector in router mode
+					if (browser) {
+						updateConfig('modelSelectorEnabled', true);
+					}
+				} else {
+					this._serverMode = ServerMode.MODEL;
+					console.info('Server running in MODEL mode (single model)');
+				}
+
 				await this.checkSlotsEndpointAvailability();
 			} catch (error) {
 				if (isSilent && hadProps) {
@@ -312,6 +375,10 @@ class ServerStore {
 		this._serverWarning = null;
 		this._loading = false;
 		this._slotsEndpointAvailable = null;
+		this._serverMode = null;
+		this._selectedModel = null;
+		this._availableModels = [];
+		this._modelLoadingStates.clear();
 		this.fetchServerPropsPromise = null;
 		this.persistServerProps(null);
 	}
@@ -329,3 +396,10 @@ export const supportsVision = () => serverStore.supportsVision;
 export const supportsAudio = () => serverStore.supportsAudio;
 export const slotsEndpointAvailable = () => serverStore.slotsEndpointAvailable;
 export const serverDefaultParams = () => serverStore.serverDefaultParams;
+
+// Server mode exports
+export const serverMode = () => serverStore.serverMode;
+export const isRouterMode = () => serverStore.isRouterMode;
+export const isModelMode = () => serverStore.isModelMode;
+export const selectedModel = () => serverStore.selectedModel;
+export const availableModels = () => serverStore.availableModels;

tools/server/webui/src/lib/types/api.d.ts

@@ -1,3 +1,4 @@
+import type { ServerModelStatus } from '$lib/enums/model';
 import type { ChatMessagePromptProgress } from './chat';
 
 export interface ApiChatMessageContentPart {
@@ -314,3 +315,74 @@ export interface ApiProcessingState {
 	promptTokens?: number;
 	cacheTokens?: number;
 }
+
+export interface ApiRouterModelMeta {
+	/** Model identifier (e.g., "unsloth/phi-4-GGUF:q4_k_m") */
+	name: string;
+	/** Path to model file or manifest */
+	path: string;
+	/** Optional path to multimodal projector */
+	path_mmproj?: string;
+	/** Whether model is in HuggingFace cache */
+	in_cache: boolean;
+	/** Port where model instance is running (0 if not loaded) */
+	port: number;
+	/** Current status of the model */
+	status: ServerModelStatus;
+	/** Error message if status is FAILED */
+	error?: string;
+}
+
+/**
+ * Request to load a model
+ */
+export interface ApiRouterModelsLoadRequest {
+	model: string;
+}
+
+/**
+ * Response from loading a model
+ */
+export interface ApiRouterModelsLoadResponse {
+	success: boolean;
+	error?: string;
+}
+
+/**
+ * Request to check model status
+ */
+export interface ApiRouterModelsStatusRequest {
+	model: string;
+}
+
+/**
+ * Response with model status
+ */
+export interface ApiRouterModelsStatusResponse {
+	model: string;
+	status: ModelStatus;
+	port?: number;
+	error?: string;
+}
+
+/**
+ * Response with list of all models
+ */
+export interface ApiRouterModelsListResponse {
+	models: ApiRouterModelMeta[];
+}
+
+/**
+ * Request to unload a model
+ */
+export interface ApiRouterModelsUnloadRequest {
+	model: string;
+}
+
+/**
+ * Response from unloading a model
+ */
+export interface ApiRouterModelsUnloadResponse {
+	success: boolean;
+	error?: string;
+}