refactor: extract constants, parameterize validators, simplify factory

Quick-win refactors from the Refactoring Guru catalog:

- Replace Magic Number with Symbolic Constant: extract DEFAULT_TIMEOUT_MS,
  DEFAULT_MAX_RETRIES, DEFAULT_MAX_TOKENS, DEFAULT_TEMPERATURE, default
  models per provider, and validation prompt into src/constants.ts.
- Parameterize Method: collapse validateTemperature / validateTopP /
  validateMaxTokens (and the inline timeout/maxRetries checks) into a
  single validateNumberInRange helper with bounds metadata.
- Inline Class / Remove Middle Man: drop the unused ProviderRegistry
  class from utils/factory.ts. createProvider now dispatches through
  the PROVIDER_REGISTRY const directly instead of a parallel switch.

Also fixes stale VERSION constant in src/index.ts (was 1.3.1).

src/providers/openwebui.ts

@@ -34,6 +34,12 @@ import type {
 } from '../types/index.js';
 import { BaseAIProvider } from './base.js';
 import { AIProviderError, AIErrorType } from '../types/index.js';
+import {
+  DEFAULT_MAX_TOKENS,
+  DEFAULT_MODELS,
+  DEFAULT_OPENWEBUI_BASE_URL,
+  DEFAULT_TEMPERATURE
+} from '../constants.js';
 
 // ============================================================================
 // TYPES AND INTERFACES
@@ -281,8 +287,8 @@ export class OpenWebUIProvider extends BaseAIProvider {
     super(config);
     
     // Set OpenWebUI-specific defaults and normalize configuration
-    this.defaultModel = config.defaultModel || 'llama3.1:latest';
-    this.baseUrl = this.normalizeBaseUrl(config.baseUrl || 'http://localhost:3000');
+    this.defaultModel = config.defaultModel || DEFAULT_MODELS.openwebui;
+    this.baseUrl = this.normalizeBaseUrl(config.baseUrl || DEFAULT_OPENWEBUI_BASE_URL);
     this.useOllamaProxy = config.useOllamaProxy ?? false;
     this.dangerouslyAllowInsecureConnections = config.dangerouslyAllowInsecureConnections ?? true;
     
@@ -689,8 +695,8 @@ export class OpenWebUIProvider extends BaseAIProvider {
     const requestBody = {
       model: params.model || this.defaultModel,
       messages: this.convertMessages(params.messages),
-      max_tokens: params.maxTokens || 1000,
-      temperature: params.temperature ?? 0.7,
+      max_tokens: params.maxTokens || DEFAULT_MAX_TOKENS,
+      temperature: params.temperature ?? DEFAULT_TEMPERATURE,
       top_p: params.topP,
       stop: params.stopSequences,
       stream: false
@@ -724,9 +730,9 @@ export class OpenWebUIProvider extends BaseAIProvider {
       prompt: prompt,
       stream: false,
       options: {
-        temperature: params.temperature ?? 0.7,
+        temperature: params.temperature ?? DEFAULT_TEMPERATURE,
         top_p: params.topP,
-        num_predict: params.maxTokens || 1000,
+        num_predict: params.maxTokens || DEFAULT_MAX_TOKENS,
         stop: params.stopSequences
       }
     };
@@ -754,8 +760,8 @@ export class OpenWebUIProvider extends BaseAIProvider {
     const requestBody = {
       model: params.model || this.defaultModel,
       messages: this.convertMessages(params.messages),
-      max_tokens: params.maxTokens || 1000,
-      temperature: params.temperature ?? 0.7,
+      max_tokens: params.maxTokens || DEFAULT_MAX_TOKENS,
+      temperature: params.temperature ?? DEFAULT_TEMPERATURE,
       top_p: params.topP,
       stop: params.stopSequences,
       stream: true
@@ -850,9 +856,9 @@ export class OpenWebUIProvider extends BaseAIProvider {
       prompt: prompt,
       stream: true,
       options: {
-        temperature: params.temperature ?? 0.7,
+        temperature: params.temperature ?? DEFAULT_TEMPERATURE,
         top_p: params.topP,
-        num_predict: params.maxTokens || 1000,
+        num_predict: params.maxTokens || DEFAULT_MAX_TOKENS,
         stop: params.stopSequences
       }
     };