@push.rocks/smartai 0.7.7 → 0.9.0

package/ts/provider.anthropic.ts

@@ -20,6 +20,7 @@ export interface IAnthropicProviderOptions {
   enableWebSearch?: boolean;
   searchDomainAllowList?: string[];
   searchDomainBlockList?: string[];
+  extendedThinking?: 'quick' | 'normal' | 'deep' | 'off';
 }
 
 export class AnthropicProvider extends MultiModalModel {
@@ -42,6 +43,25 @@ export class AnthropicProvider extends MultiModalModel {
     await super.stop();
   }
 
+  /**
+   * Returns the thinking configuration based on provider options.
+   * Defaults to 'normal' mode (8000 tokens) if not specified.
+   */
+  private getThinkingConfig(): { type: 'enabled'; budget_tokens: number } | undefined {
+    const mode = this.options.extendedThinking ?? 'normal';
+
+    const budgetMap = {
+      quick: 2048,
+      normal: 8000,
+      deep: 16000,
+      off: 0,
+    };
+
+    const budget = budgetMap[mode];
+
+    return budget > 0 ? { type: 'enabled', budget_tokens: budget } : undefined;
+  }
+
   public async chatStream(input: ReadableStream<Uint8Array>): Promise<ReadableStream<string>> {
     // Create a TextDecoder to handle incoming chunks
     const decoder = new TextDecoder();
@@ -76,12 +96,14 @@ export class AnthropicProvider extends MultiModalModel {
 
         // If we have a complete message, send it to Anthropic
         if (currentMessage) {
+          const thinkingConfig = this.getThinkingConfig();
           const stream = await this.anthropicApiClient.messages.create({
             model: 'claude-sonnet-4-5-20250929',
             messages: [{ role: currentMessage.role, content: currentMessage.content }],
             system: '',
             stream: true,
-            max_tokens: 4000,
+            max_tokens: 20000,
+            ...(thinkingConfig && { thinking: thinkingConfig }),
           });
 
           // Process each chunk from Anthropic
@@ -120,6 +142,7 @@ export class AnthropicProvider extends MultiModalModel {
       content: msg.content
     }));
 
+    const thinkingConfig = this.getThinkingConfig();
     const result = await this.anthropicApiClient.messages.create({
       model: 'claude-sonnet-4-5-20250929',
       system: optionsArg.systemMessage,
@@ -127,7 +150,8 @@ export class AnthropicProvider extends MultiModalModel {
         ...messages,
         { role: 'user' as const, content: optionsArg.userMessage }
       ],
-      max_tokens: 4000,
+      max_tokens: 20000,
+      ...(thinkingConfig && { thinking: thinkingConfig }),
     });
 
     // Extract text content from the response
@@ -167,13 +191,15 @@ export class AnthropicProvider extends MultiModalModel {
       }
     ];
 
+    const thinkingConfig = this.getThinkingConfig();
     const result = await this.anthropicApiClient.messages.create({
       model: 'claude-sonnet-4-5-20250929',
       messages: [{
         role: 'user',
         content
       }],
-      max_tokens: 1024
+      max_tokens: 10000,
+      ...(thinkingConfig && { thinking: thinkingConfig }),
     });
 
     // Extract text content from the response
@@ -229,6 +255,7 @@ export class AnthropicProvider extends MultiModalModel {
       });
     }
 
+    const thinkingConfig = this.getThinkingConfig();
     const result = await this.anthropicApiClient.messages.create({
       model: 'claude-sonnet-4-5-20250929',
       system: optionsArg.systemMessage,
@@ -236,7 +263,8 @@ export class AnthropicProvider extends MultiModalModel {
         ...messages,
         { role: 'user', content }
       ],
-      max_tokens: 4096
+      max_tokens: 20000,
+      ...(thinkingConfig && { thinking: thinkingConfig }),
     });
 
     // Extract text content from the response
@@ -286,10 +314,14 @@ export class AnthropicProvider extends MultiModalModel {
       }
 
       // Configure the request based on search depth
-      const maxTokens = optionsArg.searchDepth === 'deep' ? 8192 :
-                        optionsArg.searchDepth === 'advanced' ? 6144 : 4096;
+      const maxTokens = optionsArg.searchDepth === 'deep' ? 20000 :
+                        optionsArg.searchDepth === 'advanced' ? 20000 : 20000;
+
+      // Add thinking configuration if enabled
+      const thinkingConfig = this.getThinkingConfig();
 
       // Create the research request
+      // Note: When thinking is enabled, temperature must be 1 (or omitted)
       const requestParams: any = {
         model: 'claude-sonnet-4-5-20250929',
         system: systemMessage,
@@ -300,7 +332,8 @@ export class AnthropicProvider extends MultiModalModel {
           }
         ],
         max_tokens: maxTokens,
-        temperature: 0.7
+        // Only set temperature when thinking is NOT enabled
+        ...(thinkingConfig ? {} : { temperature: 0.7 })
       };
 
       // Add tools if web search is enabled
@@ -308,6 +341,11 @@ export class AnthropicProvider extends MultiModalModel {
         requestParams.tools = tools;
       }
 
+      // Add thinking configuration if enabled
+      if (thinkingConfig) {
+        requestParams.thinking = thinkingConfig;
+      }
+
       // Execute the research request
       const result = await this.anthropicApiClient.messages.create(requestParams);
 

package/ts/provider.elevenlabs.ts

@@ -1,4 +1,5 @@
 import * as plugins from './plugins.js';
+import { Readable } from 'stream';
 
 import { MultiModalModel } from './abstract.classes.multimodal.js';
 import type {
@@ -83,7 +84,8 @@ export class ElevenLabsProvider extends MultiModalModel {
       throw new Error(`ElevenLabs API error: ${response.status} ${response.statusText} - ${errorText}`);
     }
 
-    const nodeStream = response.streamNode();
+    const webStream = response.stream();
+    const nodeStream = Readable.fromWeb(webStream as any);
     return nodeStream;
   }
 

package/ts/provider.openai.ts

@@ -1,6 +1,7 @@
 import * as plugins from './plugins.js';
 import * as paths from './paths.js';
 import { Readable } from 'stream';
+import { toFile } from 'openai';
 
 // Custom type definition for chat completion messages
 export type TChatCompletionRequestMessage = { 
@@ -405,16 +406,19 @@ export class OpenAiProvider extends MultiModalModel {
     const model = optionsArg.model || this.options.imageModel || 'gpt-image-1';
 
     try {
+      // Convert Buffer to uploadable file format for OpenAI API
+      const imageFile = await toFile(optionsArg.image, 'image.png', { type: 'image/png' });
+
       const requestParams: any = {
         model,
-        image: optionsArg.image,
+        image: imageFile,
         prompt: optionsArg.prompt,
         n: optionsArg.n || 1,
       };
 
-      // Add mask if provided
+      // Add mask if provided (also convert to file format)
       if (optionsArg.mask) {
-        requestParams.mask = optionsArg.mask;
+        requestParams.mask = await toFile(optionsArg.mask, 'mask.png', { type: 'image/png' });
       }
 
       // Add gpt-image-1 specific parameters