webui: Architecture and UI improvements (#19596)
This commit is contained in:
committed by
GitHub
parent
2d8015e8a4
commit
baa12f3831
@@ -17,7 +17,7 @@ class LlamacppDatabase extends Dexie {
|
||||
|
||||
const db = new LlamacppDatabase();
|
||||
import { v4 as uuid } from 'uuid';
|
||||
import { MessageRole } from '$lib/enums/chat';
|
||||
import { MessageRole } from '$lib/enums';
|
||||
|
||||
export class DatabaseService {
|
||||
/**
|
||||
|
||||
@@ -1,400 +0,0 @@
|
||||
import Dexie, { type EntityTable } from 'dexie';
|
||||
import { findDescendantMessages } from '$lib/utils';
|
||||
|
||||
class LlamacppDatabase extends Dexie {
|
||||
conversations!: EntityTable<DatabaseConversation, string>;
|
||||
messages!: EntityTable<DatabaseMessage, string>;
|
||||
|
||||
constructor() {
|
||||
super('LlamacppWebui');
|
||||
|
||||
this.version(1).stores({
|
||||
conversations: 'id, lastModified, currNode, name',
|
||||
messages: 'id, convId, type, role, timestamp, parent, children'
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
const db = new LlamacppDatabase();
|
||||
import { v4 as uuid } from 'uuid';
|
||||
|
||||
/**
|
||||
* DatabaseService - Stateless IndexedDB communication layer
|
||||
*
|
||||
* **Terminology - Chat vs Conversation:**
|
||||
* - **Chat**: The active interaction space with the Chat Completions API (ephemeral, runtime).
|
||||
* - **Conversation**: The persistent database entity storing all messages and metadata.
|
||||
* This service handles raw database operations for conversations - the lowest layer
|
||||
* in the persistence stack.
|
||||
*
|
||||
* This service provides a stateless data access layer built on IndexedDB using Dexie ORM.
|
||||
* It handles all low-level storage operations for conversations and messages with support
|
||||
* for complex branching and message threading. All methods are static - no instance state.
|
||||
*
|
||||
* **Architecture & Relationships (bottom to top):**
|
||||
* - **DatabaseService** (this class): Stateless IndexedDB operations
|
||||
* - Lowest layer - direct Dexie/IndexedDB communication
|
||||
* - Pure CRUD operations without business logic
|
||||
* - Handles branching tree structure (parent-child relationships)
|
||||
* - Provides transaction safety for multi-table operations
|
||||
*
|
||||
* - **ConversationsService**: Stateless business logic layer
|
||||
* - Uses DatabaseService for all persistence operations
|
||||
* - Adds import/export, navigation, and higher-level operations
|
||||
*
|
||||
* - **conversationsStore**: Reactive state management for conversations
|
||||
* - Uses ConversationsService for database operations
|
||||
* - Manages conversation list, active conversation, and messages in memory
|
||||
*
|
||||
* - **chatStore**: Active AI interaction management
|
||||
* - Uses conversationsStore for conversation context
|
||||
* - Directly uses DatabaseService for message CRUD during streaming
|
||||
*
|
||||
* **Key Features:**
|
||||
* - **Conversation CRUD**: Create, read, update, delete conversations
|
||||
* - **Message CRUD**: Add, update, delete messages with branching support
|
||||
* - **Branch Operations**: Create branches, find descendants, cascade deletions
|
||||
* - **Transaction Safety**: Atomic operations for data consistency
|
||||
*
|
||||
* **Database Schema:**
|
||||
* - `conversations`: id, lastModified, currNode, name
|
||||
* - `messages`: id, convId, type, role, timestamp, parent, children
|
||||
*
|
||||
* **Branching Model:**
|
||||
* Messages form a tree structure where each message can have multiple children,
|
||||
* enabling conversation branching and alternative response paths. The conversation's
|
||||
* `currNode` tracks the currently active branch endpoint.
|
||||
*/
|
||||
export class DatabaseService {
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
// Conversations
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Creates a new conversation.
|
||||
*
|
||||
* @param name - Name of the conversation
|
||||
* @returns The created conversation
|
||||
*/
|
||||
static async createConversation(name: string): Promise<DatabaseConversation> {
|
||||
const conversation: DatabaseConversation = {
|
||||
id: uuid(),
|
||||
name,
|
||||
lastModified: Date.now(),
|
||||
currNode: ''
|
||||
};
|
||||
|
||||
await db.conversations.add(conversation);
|
||||
return conversation;
|
||||
}
|
||||
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
// Messages
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Creates a new message branch by adding a message and updating parent/child relationships.
|
||||
* Also updates the conversation's currNode to point to the new message.
|
||||
*
|
||||
* @param message - Message to add (without id)
|
||||
* @param parentId - Parent message ID to attach to
|
||||
* @returns The created message
|
||||
*/
|
||||
static async createMessageBranch(
|
||||
message: Omit<DatabaseMessage, 'id'>,
|
||||
parentId: string | null
|
||||
): Promise<DatabaseMessage> {
|
||||
return await db.transaction('rw', [db.conversations, db.messages], async () => {
|
||||
// Handle null parent (root message case)
|
||||
if (parentId !== null) {
|
||||
const parentMessage = await db.messages.get(parentId);
|
||||
if (!parentMessage) {
|
||||
throw new Error(`Parent message ${parentId} not found`);
|
||||
}
|
||||
}
|
||||
|
||||
const newMessage: DatabaseMessage = {
|
||||
...message,
|
||||
id: uuid(),
|
||||
parent: parentId,
|
||||
toolCalls: message.toolCalls ?? '',
|
||||
children: []
|
||||
};
|
||||
|
||||
await db.messages.add(newMessage);
|
||||
|
||||
// Update parent's children array if parent exists
|
||||
if (parentId !== null) {
|
||||
const parentMessage = await db.messages.get(parentId);
|
||||
if (parentMessage) {
|
||||
await db.messages.update(parentId, {
|
||||
children: [...parentMessage.children, newMessage.id]
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
await this.updateConversation(message.convId, {
|
||||
currNode: newMessage.id
|
||||
});
|
||||
|
||||
return newMessage;
|
||||
});
|
||||
}
|
||||
|
||||
/**
|
||||
* Creates a root message for a new conversation.
|
||||
* Root messages are not displayed but serve as the tree root for branching.
|
||||
*
|
||||
* @param convId - Conversation ID
|
||||
* @returns The created root message
|
||||
*/
|
||||
static async createRootMessage(convId: string): Promise<string> {
|
||||
const rootMessage: DatabaseMessage = {
|
||||
id: uuid(),
|
||||
convId,
|
||||
type: 'root',
|
||||
timestamp: Date.now(),
|
||||
role: 'system',
|
||||
content: '',
|
||||
parent: null,
|
||||
thinking: '',
|
||||
toolCalls: '',
|
||||
children: []
|
||||
};
|
||||
|
||||
await db.messages.add(rootMessage);
|
||||
return rootMessage.id;
|
||||
}
|
||||
|
||||
/**
|
||||
* Creates a system prompt message for a conversation.
|
||||
*
|
||||
* @param convId - Conversation ID
|
||||
* @param systemPrompt - The system prompt content (must be non-empty)
|
||||
* @param parentId - Parent message ID (typically the root message)
|
||||
* @returns The created system message
|
||||
* @throws Error if systemPrompt is empty
|
||||
*/
|
||||
static async createSystemMessage(
|
||||
convId: string,
|
||||
systemPrompt: string,
|
||||
parentId: string
|
||||
): Promise<DatabaseMessage> {
|
||||
const trimmedPrompt = systemPrompt.trim();
|
||||
if (!trimmedPrompt) {
|
||||
throw new Error('Cannot create system message with empty content');
|
||||
}
|
||||
|
||||
const systemMessage: DatabaseMessage = {
|
||||
id: uuid(),
|
||||
convId,
|
||||
type: 'system',
|
||||
timestamp: Date.now(),
|
||||
role: 'system',
|
||||
content: trimmedPrompt,
|
||||
parent: parentId,
|
||||
thinking: '',
|
||||
children: []
|
||||
};
|
||||
|
||||
await db.messages.add(systemMessage);
|
||||
|
||||
const parentMessage = await db.messages.get(parentId);
|
||||
if (parentMessage) {
|
||||
await db.messages.update(parentId, {
|
||||
children: [...parentMessage.children, systemMessage.id]
|
||||
});
|
||||
}
|
||||
|
||||
return systemMessage;
|
||||
}
|
||||
|
||||
/**
|
||||
* Deletes a conversation and all its messages.
|
||||
*
|
||||
* @param id - Conversation ID
|
||||
*/
|
||||
static async deleteConversation(id: string): Promise<void> {
|
||||
await db.transaction('rw', [db.conversations, db.messages], async () => {
|
||||
await db.conversations.delete(id);
|
||||
await db.messages.where('convId').equals(id).delete();
|
||||
});
|
||||
}
|
||||
|
||||
/**
|
||||
* Deletes a message and removes it from its parent's children array.
|
||||
*
|
||||
* @param messageId - ID of the message to delete
|
||||
*/
|
||||
static async deleteMessage(messageId: string): Promise<void> {
|
||||
await db.transaction('rw', db.messages, async () => {
|
||||
const message = await db.messages.get(messageId);
|
||||
if (!message) return;
|
||||
|
||||
// Remove this message from its parent's children array
|
||||
if (message.parent) {
|
||||
const parent = await db.messages.get(message.parent);
|
||||
if (parent) {
|
||||
parent.children = parent.children.filter((childId: string) => childId !== messageId);
|
||||
await db.messages.put(parent);
|
||||
}
|
||||
}
|
||||
|
||||
// Delete the message
|
||||
await db.messages.delete(messageId);
|
||||
});
|
||||
}
|
||||
|
||||
/**
|
||||
* Deletes a message and all its descendant messages (cascading deletion).
|
||||
* This removes the entire branch starting from the specified message.
|
||||
*
|
||||
* @param conversationId - ID of the conversation containing the message
|
||||
* @param messageId - ID of the root message to delete (along with all descendants)
|
||||
* @returns Array of all deleted message IDs
|
||||
*/
|
||||
static async deleteMessageCascading(
|
||||
conversationId: string,
|
||||
messageId: string
|
||||
): Promise<string[]> {
|
||||
return await db.transaction('rw', db.messages, async () => {
|
||||
// Get all messages in the conversation to find descendants
|
||||
const allMessages = await db.messages.where('convId').equals(conversationId).toArray();
|
||||
|
||||
// Find all descendant messages
|
||||
const descendants = findDescendantMessages(allMessages, messageId);
|
||||
const allToDelete = [messageId, ...descendants];
|
||||
|
||||
// Get the message to delete for parent cleanup
|
||||
const message = await db.messages.get(messageId);
|
||||
if (message && message.parent) {
|
||||
const parent = await db.messages.get(message.parent);
|
||||
if (parent) {
|
||||
parent.children = parent.children.filter((childId: string) => childId !== messageId);
|
||||
await db.messages.put(parent);
|
||||
}
|
||||
}
|
||||
|
||||
// Delete all messages in the branch
|
||||
await db.messages.bulkDelete(allToDelete);
|
||||
|
||||
return allToDelete;
|
||||
});
|
||||
}
|
||||
|
||||
/**
|
||||
* Gets all conversations, sorted by last modified time (newest first).
|
||||
*
|
||||
* @returns Array of conversations
|
||||
*/
|
||||
static async getAllConversations(): Promise<DatabaseConversation[]> {
|
||||
return await db.conversations.orderBy('lastModified').reverse().toArray();
|
||||
}
|
||||
|
||||
/**
|
||||
* Gets a conversation by ID.
|
||||
*
|
||||
* @param id - Conversation ID
|
||||
* @returns The conversation if found, otherwise undefined
|
||||
*/
|
||||
static async getConversation(id: string): Promise<DatabaseConversation | undefined> {
|
||||
return await db.conversations.get(id);
|
||||
}
|
||||
|
||||
/**
|
||||
* Gets all messages in a conversation, sorted by timestamp (oldest first).
|
||||
*
|
||||
* @param convId - Conversation ID
|
||||
* @returns Array of messages in the conversation
|
||||
*/
|
||||
static async getConversationMessages(convId: string): Promise<DatabaseMessage[]> {
|
||||
return await db.messages.where('convId').equals(convId).sortBy('timestamp');
|
||||
}
|
||||
|
||||
/**
|
||||
* Updates a conversation.
|
||||
*
|
||||
* @param id - Conversation ID
|
||||
* @param updates - Partial updates to apply
|
||||
* @returns Promise that resolves when the conversation is updated
|
||||
*/
|
||||
static async updateConversation(
|
||||
id: string,
|
||||
updates: Partial<Omit<DatabaseConversation, 'id'>>
|
||||
): Promise<void> {
|
||||
await db.conversations.update(id, {
|
||||
...updates,
|
||||
lastModified: Date.now()
|
||||
});
|
||||
}
|
||||
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
// Navigation
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Updates the conversation's current node (active branch).
|
||||
* This determines which conversation path is currently being viewed.
|
||||
*
|
||||
* @param convId - Conversation ID
|
||||
* @param nodeId - Message ID to set as current node
|
||||
*/
|
||||
static async updateCurrentNode(convId: string, nodeId: string): Promise<void> {
|
||||
await this.updateConversation(convId, {
|
||||
currNode: nodeId
|
||||
});
|
||||
}
|
||||
|
||||
/**
|
||||
* Updates a message.
|
||||
*
|
||||
* @param id - Message ID
|
||||
* @param updates - Partial updates to apply
|
||||
* @returns Promise that resolves when the message is updated
|
||||
*/
|
||||
static async updateMessage(
|
||||
id: string,
|
||||
updates: Partial<Omit<DatabaseMessage, 'id'>>
|
||||
): Promise<void> {
|
||||
await db.messages.update(id, updates);
|
||||
}
|
||||
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
// Import
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Imports multiple conversations and their messages.
|
||||
* Skips conversations that already exist.
|
||||
*
|
||||
* @param data - Array of { conv, messages } objects
|
||||
*/
|
||||
static async importConversations(
|
||||
data: { conv: DatabaseConversation; messages: DatabaseMessage[] }[]
|
||||
): Promise<{ imported: number; skipped: number }> {
|
||||
let importedCount = 0;
|
||||
let skippedCount = 0;
|
||||
|
||||
return await db.transaction('rw', [db.conversations, db.messages], async () => {
|
||||
for (const item of data) {
|
||||
const { conv, messages } = item;
|
||||
|
||||
const existing = await db.conversations.get(conv.id);
|
||||
if (existing) {
|
||||
console.warn(`Conversation "${conv.name}" already exists, skipping...`);
|
||||
skippedCount++;
|
||||
continue;
|
||||
}
|
||||
|
||||
await db.conversations.add(conv);
|
||||
for (const msg of messages) {
|
||||
await db.messages.put(msg);
|
||||
}
|
||||
|
||||
importedCount++;
|
||||
}
|
||||
|
||||
return { imported: importedCount, skipped: skippedCount };
|
||||
});
|
||||
}
|
||||
}
|
||||
@@ -1,5 +1,5 @@
|
||||
export { ChatService } from './chat';
|
||||
export { DatabaseService } from './database';
|
||||
export { ModelsService } from './models';
|
||||
export { PropsService } from './props';
|
||||
export { ParameterSyncService } from './parameter-sync';
|
||||
export { DatabaseService } from './database.service';
|
||||
export { ModelsService } from './models.service';
|
||||
export { PropsService } from './props.service';
|
||||
export { ParameterSyncService, SYNCABLE_PARAMETERS } from './parameter-sync.service';
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import { ServerModelStatus } from '$lib/enums';
|
||||
import { apiFetch, apiPost } from '$lib/utils/api-fetch';
|
||||
import { apiFetch, apiPost } from '$lib/utils';
|
||||
|
||||
export class ModelsService {
|
||||
/**
|
||||
|
||||
@@ -1,124 +0,0 @@
|
||||
import { base } from '$app/paths';
|
||||
import { ServerModelStatus } from '$lib/enums';
|
||||
import { getJsonHeaders } from '$lib/utils';
|
||||
|
||||
/**
|
||||
* ModelsService - Stateless service for model management API communication
|
||||
*
|
||||
* This service handles communication with model-related endpoints:
|
||||
* - `/v1/models` - OpenAI-compatible model list (MODEL + ROUTER mode)
|
||||
* - `/models/load`, `/models/unload` - Router-specific model management (ROUTER mode only)
|
||||
*
|
||||
* **Responsibilities:**
|
||||
* - List available models
|
||||
* - Load/unload models (ROUTER mode)
|
||||
* - Check model status (ROUTER mode)
|
||||
*
|
||||
* **Used by:**
|
||||
* - modelsStore: Primary consumer for model state management
|
||||
*/
|
||||
export class ModelsService {
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
// Listing
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Fetch list of models from OpenAI-compatible endpoint
|
||||
* Works in both MODEL and ROUTER modes
|
||||
*/
|
||||
static async list(): Promise<ApiModelListResponse> {
|
||||
const response = await fetch(`${base}/v1/models`, {
|
||||
headers: getJsonHeaders()
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
throw new Error(`Failed to fetch model list (status ${response.status})`);
|
||||
}
|
||||
|
||||
return response.json() as Promise<ApiModelListResponse>;
|
||||
}
|
||||
|
||||
/**
|
||||
* Fetch list of all models with detailed metadata (ROUTER mode)
|
||||
* Returns models with load status, paths, and other metadata
|
||||
*/
|
||||
static async listRouter(): Promise<ApiRouterModelsListResponse> {
|
||||
const response = await fetch(`${base}/v1/models`, {
|
||||
headers: getJsonHeaders()
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
throw new Error(`Failed to fetch router models list (status ${response.status})`);
|
||||
}
|
||||
|
||||
return response.json() as Promise<ApiRouterModelsListResponse>;
|
||||
}
|
||||
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
// Load/Unload
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Load a model (ROUTER mode)
|
||||
* POST /models/load
|
||||
* @param modelId - Model identifier to load
|
||||
* @param extraArgs - Optional additional arguments to pass to the model instance
|
||||
*/
|
||||
static async load(modelId: string, extraArgs?: string[]): Promise<ApiRouterModelsLoadResponse> {
|
||||
const payload: { model: string; extra_args?: string[] } = { model: modelId };
|
||||
if (extraArgs && extraArgs.length > 0) {
|
||||
payload.extra_args = extraArgs;
|
||||
}
|
||||
|
||||
const response = await fetch(`${base}/models/load`, {
|
||||
method: 'POST',
|
||||
headers: getJsonHeaders(),
|
||||
body: JSON.stringify(payload)
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
const errorData = await response.json().catch(() => ({}));
|
||||
throw new Error(errorData.error || `Failed to load model (status ${response.status})`);
|
||||
}
|
||||
|
||||
return response.json() as Promise<ApiRouterModelsLoadResponse>;
|
||||
}
|
||||
|
||||
/**
|
||||
* Unload a model (ROUTER mode)
|
||||
* POST /models/unload
|
||||
* @param modelId - Model identifier to unload
|
||||
*/
|
||||
static async unload(modelId: string): Promise<ApiRouterModelsUnloadResponse> {
|
||||
const response = await fetch(`${base}/models/unload`, {
|
||||
method: 'POST',
|
||||
headers: getJsonHeaders(),
|
||||
body: JSON.stringify({ model: modelId })
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
const errorData = await response.json().catch(() => ({}));
|
||||
throw new Error(errorData.error || `Failed to unload model (status ${response.status})`);
|
||||
}
|
||||
|
||||
return response.json() as Promise<ApiRouterModelsUnloadResponse>;
|
||||
}
|
||||
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
// Status
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Check if a model is loaded based on its metadata
|
||||
*/
|
||||
static isModelLoaded(model: ApiModelDataEntry): boolean {
|
||||
return model.status.value === ServerModelStatus.LOADED;
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if a model is currently loading
|
||||
*/
|
||||
static isModelLoading(model: ApiModelDataEntry): boolean {
|
||||
return model.status.value === ServerModelStatus.LOADING;
|
||||
}
|
||||
}
|
||||
@@ -1,22 +1,6 @@
|
||||
import { normalizeFloatingPoint } from '$lib/utils';
|
||||
import { SyncableParameterType, ParameterSource } from '$lib/enums/settings';
|
||||
|
||||
type ParameterValue = string | number | boolean;
|
||||
type ParameterRecord = Record<string, ParameterValue>;
|
||||
|
||||
interface ParameterInfo {
|
||||
value: string | number | boolean;
|
||||
source: ParameterSource;
|
||||
serverDefault?: string | number | boolean;
|
||||
userOverride?: string | number | boolean;
|
||||
}
|
||||
|
||||
interface SyncableParameter {
|
||||
key: string;
|
||||
serverKey: string;
|
||||
type: SyncableParameterType;
|
||||
canSync: boolean;
|
||||
}
|
||||
import type { SyncableParameter, ParameterRecord, ParameterInfo, ParameterValue } from '$lib/types';
|
||||
import { SyncableParameterType, ParameterSource } from '$lib/enums';
|
||||
|
||||
/**
|
||||
* Mapping of webui setting keys to server parameter keys.
|
||||
|
||||
@@ -1,148 +0,0 @@
|
||||
import { describe, it, expect } from 'vitest';
|
||||
import { ParameterSyncService } from './parameter-sync';
|
||||
|
||||
describe('ParameterSyncService', () => {
|
||||
describe('roundFloatingPoint', () => {
|
||||
it('should fix JavaScript floating-point precision issues', () => {
|
||||
// Test the specific values from the screenshot
|
||||
const mockServerParams = {
|
||||
top_p: 0.949999988079071,
|
||||
min_p: 0.009999999776482582,
|
||||
temperature: 0.800000011920929,
|
||||
top_k: 40,
|
||||
samplers: ['top_k', 'typ_p', 'top_p', 'min_p', 'temperature']
|
||||
};
|
||||
|
||||
const result = ParameterSyncService.extractServerDefaults({
|
||||
...mockServerParams,
|
||||
// Add other required fields to match the API type
|
||||
n_predict: 512,
|
||||
seed: -1,
|
||||
dynatemp_range: 0.0,
|
||||
dynatemp_exponent: 1.0,
|
||||
xtc_probability: 0.0,
|
||||
xtc_threshold: 0.1,
|
||||
typ_p: 1.0,
|
||||
repeat_last_n: 64,
|
||||
repeat_penalty: 1.0,
|
||||
presence_penalty: 0.0,
|
||||
frequency_penalty: 0.0,
|
||||
dry_multiplier: 0.0,
|
||||
dry_base: 1.75,
|
||||
dry_allowed_length: 2,
|
||||
dry_penalty_last_n: -1,
|
||||
mirostat: 0,
|
||||
mirostat_tau: 5.0,
|
||||
mirostat_eta: 0.1,
|
||||
stop: [],
|
||||
max_tokens: -1,
|
||||
n_keep: 0,
|
||||
n_discard: 0,
|
||||
ignore_eos: false,
|
||||
stream: true,
|
||||
logit_bias: [],
|
||||
n_probs: 0,
|
||||
min_keep: 0,
|
||||
grammar: '',
|
||||
grammar_lazy: false,
|
||||
grammar_triggers: [],
|
||||
preserved_tokens: [],
|
||||
chat_format: '',
|
||||
reasoning_format: '',
|
||||
reasoning_in_content: false,
|
||||
thinking_forced_open: false,
|
||||
'speculative.n_max': 0,
|
||||
'speculative.n_min': 0,
|
||||
'speculative.p_min': 0.0,
|
||||
timings_per_token: false,
|
||||
post_sampling_probs: false,
|
||||
lora: [],
|
||||
top_n_sigma: 0.0,
|
||||
dry_sequence_breakers: []
|
||||
} as ApiLlamaCppServerProps['default_generation_settings']['params']);
|
||||
|
||||
// Check that the problematic floating-point values are rounded correctly
|
||||
expect(result.top_p).toBe(0.95);
|
||||
expect(result.min_p).toBe(0.01);
|
||||
expect(result.temperature).toBe(0.8);
|
||||
expect(result.top_k).toBe(40); // Integer should remain unchanged
|
||||
expect(result.samplers).toBe('top_k;typ_p;top_p;min_p;temperature');
|
||||
});
|
||||
|
||||
it('should preserve non-numeric values', () => {
|
||||
const mockServerParams = {
|
||||
samplers: ['top_k', 'temperature'],
|
||||
max_tokens: -1,
|
||||
temperature: 0.7
|
||||
};
|
||||
|
||||
const result = ParameterSyncService.extractServerDefaults({
|
||||
...mockServerParams,
|
||||
// Minimal required fields
|
||||
n_predict: 512,
|
||||
seed: -1,
|
||||
dynatemp_range: 0.0,
|
||||
dynatemp_exponent: 1.0,
|
||||
top_k: 40,
|
||||
top_p: 0.95,
|
||||
min_p: 0.05,
|
||||
xtc_probability: 0.0,
|
||||
xtc_threshold: 0.1,
|
||||
typ_p: 1.0,
|
||||
repeat_last_n: 64,
|
||||
repeat_penalty: 1.0,
|
||||
presence_penalty: 0.0,
|
||||
frequency_penalty: 0.0,
|
||||
dry_multiplier: 0.0,
|
||||
dry_base: 1.75,
|
||||
dry_allowed_length: 2,
|
||||
dry_penalty_last_n: -1,
|
||||
mirostat: 0,
|
||||
mirostat_tau: 5.0,
|
||||
mirostat_eta: 0.1,
|
||||
stop: [],
|
||||
n_keep: 0,
|
||||
n_discard: 0,
|
||||
ignore_eos: false,
|
||||
stream: true,
|
||||
logit_bias: [],
|
||||
n_probs: 0,
|
||||
min_keep: 0,
|
||||
grammar: '',
|
||||
grammar_lazy: false,
|
||||
grammar_triggers: [],
|
||||
preserved_tokens: [],
|
||||
chat_format: '',
|
||||
reasoning_format: '',
|
||||
reasoning_in_content: false,
|
||||
thinking_forced_open: false,
|
||||
'speculative.n_max': 0,
|
||||
'speculative.n_min': 0,
|
||||
'speculative.p_min': 0.0,
|
||||
timings_per_token: false,
|
||||
post_sampling_probs: false,
|
||||
lora: [],
|
||||
top_n_sigma: 0.0,
|
||||
dry_sequence_breakers: []
|
||||
} as ApiLlamaCppServerProps['default_generation_settings']['params']);
|
||||
|
||||
expect(result.samplers).toBe('top_k;temperature');
|
||||
expect(result.max_tokens).toBe(-1);
|
||||
expect(result.temperature).toBe(0.7);
|
||||
});
|
||||
|
||||
it('should merge webui settings from props when provided', () => {
|
||||
const result = ParameterSyncService.extractServerDefaults(null, {
|
||||
pasteLongTextToFileLen: 0,
|
||||
pdfAsImage: true,
|
||||
renderUserContentAsMarkdown: false,
|
||||
theme: 'dark'
|
||||
});
|
||||
|
||||
expect(result.pasteLongTextToFileLen).toBe(0);
|
||||
expect(result.pdfAsImage).toBe(true);
|
||||
expect(result.renderUserContentAsMarkdown).toBe(false);
|
||||
expect(result.theme).toBeUndefined();
|
||||
});
|
||||
});
|
||||
});
|
||||
@@ -1,273 +0,0 @@
|
||||
/**
|
||||
* ParameterSyncService - Handles synchronization between server defaults and user settings
|
||||
*
|
||||
* This service manages the complex logic of merging server-provided default parameters
|
||||
* with user-configured overrides, ensuring the UI reflects the actual server state
|
||||
* while preserving user customizations.
|
||||
*
|
||||
* **Key Responsibilities:**
|
||||
* - Extract syncable parameters from server props
|
||||
* - Merge server defaults with user overrides
|
||||
* - Track parameter sources (server, user, default)
|
||||
* - Provide sync utilities for settings store integration
|
||||
*/
|
||||
|
||||
import { normalizeFloatingPoint } from '$lib/utils';
|
||||
|
||||
export type ParameterSource = 'default' | 'custom';
|
||||
export type ParameterValue = string | number | boolean;
|
||||
export type ParameterRecord = Record<string, ParameterValue>;
|
||||
|
||||
export interface ParameterInfo {
|
||||
value: string | number | boolean;
|
||||
source: ParameterSource;
|
||||
serverDefault?: string | number | boolean;
|
||||
userOverride?: string | number | boolean;
|
||||
}
|
||||
|
||||
export interface SyncableParameter {
|
||||
key: string;
|
||||
serverKey: string;
|
||||
type: 'number' | 'string' | 'boolean';
|
||||
canSync: boolean;
|
||||
}
|
||||
|
||||
/**
|
||||
* Mapping of webui setting keys to server parameter keys
|
||||
* Only parameters that should be synced from server are included
|
||||
*/
|
||||
export const SYNCABLE_PARAMETERS: SyncableParameter[] = [
|
||||
{ key: 'temperature', serverKey: 'temperature', type: 'number', canSync: true },
|
||||
{ key: 'top_k', serverKey: 'top_k', type: 'number', canSync: true },
|
||||
{ key: 'top_p', serverKey: 'top_p', type: 'number', canSync: true },
|
||||
{ key: 'min_p', serverKey: 'min_p', type: 'number', canSync: true },
|
||||
{ key: 'dynatemp_range', serverKey: 'dynatemp_range', type: 'number', canSync: true },
|
||||
{ key: 'dynatemp_exponent', serverKey: 'dynatemp_exponent', type: 'number', canSync: true },
|
||||
{ key: 'xtc_probability', serverKey: 'xtc_probability', type: 'number', canSync: true },
|
||||
{ key: 'xtc_threshold', serverKey: 'xtc_threshold', type: 'number', canSync: true },
|
||||
{ key: 'typ_p', serverKey: 'typ_p', type: 'number', canSync: true },
|
||||
{ key: 'repeat_last_n', serverKey: 'repeat_last_n', type: 'number', canSync: true },
|
||||
{ key: 'repeat_penalty', serverKey: 'repeat_penalty', type: 'number', canSync: true },
|
||||
{ key: 'presence_penalty', serverKey: 'presence_penalty', type: 'number', canSync: true },
|
||||
{ key: 'frequency_penalty', serverKey: 'frequency_penalty', type: 'number', canSync: true },
|
||||
{ key: 'dry_multiplier', serverKey: 'dry_multiplier', type: 'number', canSync: true },
|
||||
{ key: 'dry_base', serverKey: 'dry_base', type: 'number', canSync: true },
|
||||
{ key: 'dry_allowed_length', serverKey: 'dry_allowed_length', type: 'number', canSync: true },
|
||||
{ key: 'dry_penalty_last_n', serverKey: 'dry_penalty_last_n', type: 'number', canSync: true },
|
||||
{ key: 'max_tokens', serverKey: 'max_tokens', type: 'number', canSync: true },
|
||||
{ key: 'samplers', serverKey: 'samplers', type: 'string', canSync: true },
|
||||
{
|
||||
key: 'pasteLongTextToFileLen',
|
||||
serverKey: 'pasteLongTextToFileLen',
|
||||
type: 'number',
|
||||
canSync: true
|
||||
},
|
||||
{ key: 'pdfAsImage', serverKey: 'pdfAsImage', type: 'boolean', canSync: true },
|
||||
{
|
||||
key: 'showThoughtInProgress',
|
||||
serverKey: 'showThoughtInProgress',
|
||||
type: 'boolean',
|
||||
canSync: true
|
||||
},
|
||||
{ key: 'showToolCalls', serverKey: 'showToolCalls', type: 'boolean', canSync: true },
|
||||
{ key: 'keepStatsVisible', serverKey: 'keepStatsVisible', type: 'boolean', canSync: true },
|
||||
{ key: 'showMessageStats', serverKey: 'showMessageStats', type: 'boolean', canSync: true },
|
||||
{
|
||||
key: 'askForTitleConfirmation',
|
||||
serverKey: 'askForTitleConfirmation',
|
||||
type: 'boolean',
|
||||
canSync: true
|
||||
},
|
||||
{ key: 'disableAutoScroll', serverKey: 'disableAutoScroll', type: 'boolean', canSync: true },
|
||||
{
|
||||
key: 'renderUserContentAsMarkdown',
|
||||
serverKey: 'renderUserContentAsMarkdown',
|
||||
type: 'boolean',
|
||||
canSync: true
|
||||
},
|
||||
{ key: 'autoMicOnEmpty', serverKey: 'autoMicOnEmpty', type: 'boolean', canSync: true },
|
||||
{
|
||||
key: 'pyInterpreterEnabled',
|
||||
serverKey: 'pyInterpreterEnabled',
|
||||
type: 'boolean',
|
||||
canSync: true
|
||||
},
|
||||
{
|
||||
key: 'enableContinueGeneration',
|
||||
serverKey: 'enableContinueGeneration',
|
||||
type: 'boolean',
|
||||
canSync: true
|
||||
}
|
||||
];
|
||||
|
||||
export class ParameterSyncService {
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
// Extraction
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Round floating-point numbers to avoid JavaScript precision issues
|
||||
*/
|
||||
private static roundFloatingPoint(value: ParameterValue): ParameterValue {
|
||||
return normalizeFloatingPoint(value) as ParameterValue;
|
||||
}
|
||||
|
||||
/**
|
||||
* Extract server default parameters that can be synced
|
||||
*/
|
||||
static extractServerDefaults(
|
||||
serverParams: ApiLlamaCppServerProps['default_generation_settings']['params'] | null,
|
||||
webuiSettings?: Record<string, string | number | boolean>
|
||||
): ParameterRecord {
|
||||
const extracted: ParameterRecord = {};
|
||||
|
||||
if (serverParams) {
|
||||
for (const param of SYNCABLE_PARAMETERS) {
|
||||
if (param.canSync && param.serverKey in serverParams) {
|
||||
const value = (serverParams as unknown as Record<string, ParameterValue>)[
|
||||
param.serverKey
|
||||
];
|
||||
if (value !== undefined) {
|
||||
// Apply precision rounding to avoid JavaScript floating-point issues
|
||||
extracted[param.key] = this.roundFloatingPoint(value);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Handle samplers array conversion to string
|
||||
if (serverParams.samplers && Array.isArray(serverParams.samplers)) {
|
||||
extracted.samplers = serverParams.samplers.join(';');
|
||||
}
|
||||
}
|
||||
|
||||
if (webuiSettings) {
|
||||
for (const param of SYNCABLE_PARAMETERS) {
|
||||
if (param.canSync && param.serverKey in webuiSettings) {
|
||||
const value = webuiSettings[param.serverKey];
|
||||
if (value !== undefined) {
|
||||
extracted[param.key] = this.roundFloatingPoint(value);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return extracted;
|
||||
}
|
||||
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
// Merging
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Merge server defaults with current user settings
|
||||
* Returns updated settings that respect user overrides while using server defaults
|
||||
*/
|
||||
static mergeWithServerDefaults(
|
||||
currentSettings: ParameterRecord,
|
||||
serverDefaults: ParameterRecord,
|
||||
userOverrides: Set<string> = new Set()
|
||||
): ParameterRecord {
|
||||
const merged = { ...currentSettings };
|
||||
|
||||
for (const [key, serverValue] of Object.entries(serverDefaults)) {
|
||||
// Only update if user hasn't explicitly overridden this parameter
|
||||
if (!userOverrides.has(key)) {
|
||||
merged[key] = this.roundFloatingPoint(serverValue);
|
||||
}
|
||||
}
|
||||
|
||||
return merged;
|
||||
}
|
||||
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
// Info
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Get parameter information including source and values
|
||||
*/
|
||||
static getParameterInfo(
|
||||
key: string,
|
||||
currentValue: ParameterValue,
|
||||
propsDefaults: ParameterRecord,
|
||||
userOverrides: Set<string>
|
||||
): ParameterInfo {
|
||||
const hasPropsDefault = propsDefaults[key] !== undefined;
|
||||
const isUserOverride = userOverrides.has(key);
|
||||
|
||||
// Simple logic: either using default (from props) or custom (user override)
|
||||
const source: ParameterSource = isUserOverride ? 'custom' : 'default';
|
||||
|
||||
return {
|
||||
value: currentValue,
|
||||
source,
|
||||
serverDefault: hasPropsDefault ? propsDefaults[key] : undefined, // Keep same field name for compatibility
|
||||
userOverride: isUserOverride ? currentValue : undefined
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if a parameter can be synced from server
|
||||
*/
|
||||
static canSyncParameter(key: string): boolean {
|
||||
return SYNCABLE_PARAMETERS.some((param) => param.key === key && param.canSync);
|
||||
}
|
||||
|
||||
/**
|
||||
* Get all syncable parameter keys
|
||||
*/
|
||||
static getSyncableParameterKeys(): string[] {
|
||||
return SYNCABLE_PARAMETERS.filter((param) => param.canSync).map((param) => param.key);
|
||||
}
|
||||
|
||||
/**
|
||||
* Validate server parameter value
|
||||
*/
|
||||
static validateServerParameter(key: string, value: ParameterValue): boolean {
|
||||
const param = SYNCABLE_PARAMETERS.find((p) => p.key === key);
|
||||
if (!param) return false;
|
||||
|
||||
switch (param.type) {
|
||||
case 'number':
|
||||
return typeof value === 'number' && !isNaN(value);
|
||||
case 'string':
|
||||
return typeof value === 'string';
|
||||
case 'boolean':
|
||||
return typeof value === 'boolean';
|
||||
default:
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
// Diff
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Create a diff between current settings and server defaults
|
||||
*/
|
||||
static createParameterDiff(
|
||||
currentSettings: ParameterRecord,
|
||||
serverDefaults: ParameterRecord
|
||||
): Record<string, { current: ParameterValue; server: ParameterValue; differs: boolean }> {
|
||||
const diff: Record<
|
||||
string,
|
||||
{ current: ParameterValue; server: ParameterValue; differs: boolean }
|
||||
> = {};
|
||||
|
||||
for (const key of this.getSyncableParameterKeys()) {
|
||||
const currentValue = currentSettings[key];
|
||||
const serverValue = serverDefaults[key];
|
||||
|
||||
if (serverValue !== undefined) {
|
||||
diff[key] = {
|
||||
current: currentValue,
|
||||
server: serverValue,
|
||||
differs: currentValue !== serverValue
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
return diff;
|
||||
}
|
||||
}
|
||||
@@ -1,4 +1,4 @@
|
||||
import { apiFetchWithParams } from '$lib/utils/api-fetch';
|
||||
import { apiFetchWithParams } from '$lib/utils';
|
||||
|
||||
export class PropsService {
|
||||
/**
|
||||
|
||||
@@ -1,77 +0,0 @@
|
||||
import { getAuthHeaders } from '$lib/utils';
|
||||
|
||||
/**
|
||||
* PropsService - Server properties management
|
||||
*
|
||||
* This service handles communication with the /props endpoint to retrieve
|
||||
* server configuration, model information, and capabilities.
|
||||
*
|
||||
* **Responsibilities:**
|
||||
* - Fetch server properties from /props endpoint
|
||||
* - Handle API authentication
|
||||
* - Parse and validate server response
|
||||
*
|
||||
* **Used by:**
|
||||
* - serverStore: Primary consumer for server state management
|
||||
*/
|
||||
export class PropsService {
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
// Fetching
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Fetches server properties from the /props endpoint
|
||||
*
|
||||
* @param autoload - If false, prevents automatic model loading (default: false)
|
||||
* @returns {Promise<ApiLlamaCppServerProps>} Server properties
|
||||
* @throws {Error} If the request fails or returns invalid data
|
||||
*/
|
||||
static async fetch(autoload = false): Promise<ApiLlamaCppServerProps> {
|
||||
const url = new URL('./props', window.location.href);
|
||||
if (!autoload) {
|
||||
url.searchParams.set('autoload', 'false');
|
||||
}
|
||||
|
||||
const response = await fetch(url.toString(), {
|
||||
headers: getAuthHeaders()
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
throw new Error(
|
||||
`Failed to fetch server properties: ${response.status} ${response.statusText}`
|
||||
);
|
||||
}
|
||||
|
||||
const data = await response.json();
|
||||
return data as ApiLlamaCppServerProps;
|
||||
}
|
||||
|
||||
/**
|
||||
* Fetches server properties for a specific model (ROUTER mode)
|
||||
*
|
||||
* @param modelId - The model ID to fetch properties for
|
||||
* @param autoload - If false, prevents automatic model loading (default: false)
|
||||
* @returns {Promise<ApiLlamaCppServerProps>} Server properties for the model
|
||||
* @throws {Error} If the request fails or returns invalid data
|
||||
*/
|
||||
static async fetchForModel(modelId: string, autoload = false): Promise<ApiLlamaCppServerProps> {
|
||||
const url = new URL('./props', window.location.href);
|
||||
url.searchParams.set('model', modelId);
|
||||
if (!autoload) {
|
||||
url.searchParams.set('autoload', 'false');
|
||||
}
|
||||
|
||||
const response = await fetch(url.toString(), {
|
||||
headers: getAuthHeaders()
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
throw new Error(
|
||||
`Failed to fetch model properties: ${response.status} ${response.statusText}`
|
||||
);
|
||||
}
|
||||
|
||||
const data = await response.json();
|
||||
return data as ApiLlamaCppServerProps;
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user