feat(providers): Add research API and image generation/editing support; extend providers and tests

ts/provider.openai.ts

@@ -9,7 +9,13 @@ export type TChatCompletionRequestMessage = {
 };
 
 import { MultiModalModel } from './abstract.classes.multimodal.js';
-import type { ResearchOptions, ResearchResponse } from './abstract.classes.multimodal.js';
+import type {
+  ResearchOptions,
+  ResearchResponse,
+  ImageGenerateOptions,
+  ImageEditOptions,
+  ImageResponse
+} from './abstract.classes.multimodal.js';
 
 export interface IOpenaiProviderOptions {
   openaiToken: string;
@@ -17,6 +23,7 @@ export interface IOpenaiProviderOptions {
   audioModel?: string;
   visionModel?: string;
   researchModel?: string;
+  imageModel?: string;
   enableWebSearch?: boolean;
 }
 
@@ -328,4 +335,121 @@ export class OpenAiProvider extends MultiModalModel {
       throw new Error(`Failed to perform research: ${error.message}`);
     }
   }
+
+  /**
+   * Image generation using OpenAI's gpt-image-1 or DALL-E models
+   */
+  public async imageGenerate(optionsArg: ImageGenerateOptions): Promise<ImageResponse> {
+    const model = optionsArg.model || this.options.imageModel || 'gpt-image-1';
+
+    try {
+      const requestParams: any = {
+        model,
+        prompt: optionsArg.prompt,
+        n: optionsArg.n || 1,
+      };
+
+      // Add gpt-image-1 specific parameters
+      if (model === 'gpt-image-1') {
+        if (optionsArg.quality) requestParams.quality = optionsArg.quality;
+        if (optionsArg.size) requestParams.size = optionsArg.size;
+        if (optionsArg.background) requestParams.background = optionsArg.background;
+        if (optionsArg.outputFormat) requestParams.output_format = optionsArg.outputFormat;
+        if (optionsArg.outputCompression !== undefined) requestParams.output_compression = optionsArg.outputCompression;
+        if (optionsArg.moderation) requestParams.moderation = optionsArg.moderation;
+        if (optionsArg.stream !== undefined) requestParams.stream = optionsArg.stream;
+        if (optionsArg.partialImages !== undefined) requestParams.partial_images = optionsArg.partialImages;
+      } else if (model === 'dall-e-3') {
+        // DALL-E 3 specific parameters
+        if (optionsArg.quality) requestParams.quality = optionsArg.quality;
+        if (optionsArg.size) requestParams.size = optionsArg.size;
+        if (optionsArg.style) requestParams.style = optionsArg.style;
+        requestParams.response_format = 'b64_json'; // Always use base64 for consistency
+      } else if (model === 'dall-e-2') {
+        // DALL-E 2 specific parameters
+        if (optionsArg.size) requestParams.size = optionsArg.size;
+        requestParams.response_format = 'b64_json';
+      }
+
+      const result = await this.openAiApiClient.images.generate(requestParams);
+
+      const images = (result.data || []).map(img => ({
+        b64_json: img.b64_json,
+        url: img.url,
+        revisedPrompt: img.revised_prompt
+      }));
+
+      return {
+        images,
+        metadata: {
+          model,
+          quality: result.quality,
+          size: result.size,
+          outputFormat: result.output_format,
+          tokensUsed: result.usage?.total_tokens
+        }
+      };
+    } catch (error) {
+      console.error('Image generation error:', error);
+      throw new Error(`Failed to generate image: ${error.message}`);
+    }
+  }
+
+  /**
+   * Image editing using OpenAI's gpt-image-1 or DALL-E 2 models
+   */
+  public async imageEdit(optionsArg: ImageEditOptions): Promise<ImageResponse> {
+    const model = optionsArg.model || this.options.imageModel || 'gpt-image-1';
+
+    try {
+      const requestParams: any = {
+        model,
+        image: optionsArg.image,
+        prompt: optionsArg.prompt,
+        n: optionsArg.n || 1,
+      };
+
+      // Add mask if provided
+      if (optionsArg.mask) {
+        requestParams.mask = optionsArg.mask;
+      }
+
+      // Add gpt-image-1 specific parameters
+      if (model === 'gpt-image-1') {
+        if (optionsArg.quality) requestParams.quality = optionsArg.quality;
+        if (optionsArg.size) requestParams.size = optionsArg.size;
+        if (optionsArg.background) requestParams.background = optionsArg.background;
+        if (optionsArg.outputFormat) requestParams.output_format = optionsArg.outputFormat;
+        if (optionsArg.outputCompression !== undefined) requestParams.output_compression = optionsArg.outputCompression;
+        if (optionsArg.stream !== undefined) requestParams.stream = optionsArg.stream;
+        if (optionsArg.partialImages !== undefined) requestParams.partial_images = optionsArg.partialImages;
+      } else if (model === 'dall-e-2') {
+        // DALL-E 2 specific parameters
+        if (optionsArg.size) requestParams.size = optionsArg.size;
+        requestParams.response_format = 'b64_json';
+      }
+
+      const result = await this.openAiApiClient.images.edit(requestParams);
+
+      const images = (result.data || []).map(img => ({
+        b64_json: img.b64_json,
+        url: img.url,
+        revisedPrompt: img.revised_prompt
+      }));
+
+      return {
+        images,
+        metadata: {
+          model,
+          quality: result.quality,
+          size: result.size,
+          outputFormat: result.output_format,
+          tokensUsed: result.usage?.total_tokens
+        }
+      };
+    } catch (error) {
+      console.error('Image edit error:', error);
+      throw new Error(`Failed to edit image: ${error.message}`);
+    }
+  }
 }