Update vision capability detection to include GPT-5 series, o-series models, and Mistral Pixtral

- Added GPT-5 series (gpt-5.1, gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro) to vision detection
- Added o-series reasoning models (o1, o3, o4-mini) to vision detection
- Added Mistral Pixtral models (pixtral-large, pixtral-12b) to vision detection
- Updated vision detection in modelRouter.ts and chatThreadService.ts
- Updated routingSmokeTests.ts to include new vision models in test validation
- Updated documentation to reflect expanded vision model support

Author: Tajudeen

docs/CortexIDE-vs-Other-AI-Editors.md

@@ -340,7 +340,7 @@ This comparison is based on:
 **CortexIDE**: ✅ **Yes** - Extensive model support verified in `modelCapabilities.ts`:
 - **15+ providers**: OpenAI, Anthropic, xAI, Gemini, DeepSeek, Groq, Mistral, OpenRouter, Ollama, vLLM, LM Studio, OpenAI-compatible, LiteLLM, Google Vertex, Microsoft Azure, AWS Bedrock
 - **Reasoning models**: o1, o3, Claude 3.7/4, DeepSeek R1, QwQ, Qwen3, Phi-4
-- **Vision models**: GPT-4o, Claude 3.5/4, Gemini, local VLMs
+- **Vision models**: GPT-4o, GPT-4.1, GPT-5 series, o-series (o1, o3, o4-mini), Claude 3.5/4, Gemini (all models), Pixtral, local VLMs
 - **FIM models**: Codestral, Qwen2.5-coder, StarCoder2
 
 **Cursor**: ✅ **Yes** - Wide model support.
@@ -361,6 +361,8 @@ This comparison is based on:
 - Vision-capable model detection (verified in `modelRouter.ts:1400-1417`)
 - Image QA registry (verified in `imageQARegistryContribution.ts`)
 - Multimodal message handling (verified in `convertToLLMMessageService.ts`)
+- Supports image uploads for: GPT-4o, GPT-4.1, GPT-5 series, o-series, Claude 3.5/4, Gemini (all), Pixtral, local VLMs
+- PDF upload support with text extraction and vision-based processing
 
 **Cursor**: ✅ **Yes** - Vision model support.
 
@@ -500,10 +502,11 @@ For a detailed list of models supported by CortexIDE, see the [Supported Models
 
 CortexIDE supports 15+ providers with 100+ models, including:
 - Reasoning models (o1, o3, Claude 3.7/4, DeepSeek R1, QwQ, Qwen3, Phi-4)
-- Vision models (GPT-4o, Claude 3.5/4, Gemini, local VLMs)
+- Vision models (GPT-4o, GPT-4.1, GPT-5 series, o-series, Claude 3.5/4, Gemini, Pixtral, local VLMs)
 - FIM models (Codestral, Qwen2.5-coder, StarCoder2)
 - Local models (Ollama, vLLM, LM Studio)
 
+
 ## Conclusion
 
 CortexIDE stands out as the **only fully open-source AI code editor** with:
@@ -526,3 +529,5 @@ While other tools excel in specific areas (Cursor's polish, Continue.dev's VS Co
 
 If you find any inaccuracies, please [open an issue](https://github.com/cortexide/cortexide/issues/new) with corrections and sources.
 
+
+

src/vs/workbench/contrib/cortexide/browser/chatThreadService.ts

@@ -818,7 +818,20 @@ class ChatThreadService extends Disposable implements IChatThreadService {
 			return name.includes('3.5') || name.includes('3.7') || name.includes('4') || name.includes('opus') || name.includes('sonnet');
 		}
 		if (provider === 'openai') {
-			return name.includes('4o') || name.includes('4.1') || name.includes('gpt-4');
+			// GPT-5 series (all variants support vision)
+			if (name.includes('gpt-5') || name.includes('gpt-5.1')) return true;
+			// GPT-4.1 series
+			if (name.includes('4.1')) return true;
+			// GPT-4o series
+			if (name.includes('4o')) return true;
+			// o-series reasoning models (o1, o3, o4-mini support vision)
+			if (name.startsWith('o1') || name.startsWith('o3') || name.startsWith('o4')) return true;
+			// Legacy GPT-4 models
+			if (name.includes('gpt-4')) return true;
+		}
+		if (provider === 'mistral') {
+			// Pixtral models support vision
+			if (name.includes('pixtral')) return true;
 		}
 		if (provider === 'ollama' || provider === 'vllm') {
 			return name.includes('llava') || name.includes('bakllava') || name.includes('vision');

src/vs/workbench/contrib/cortexide/common/modelRouter.ts

@@ -1407,7 +1407,20 @@ export class TaskAwareModelRouter extends Disposable implements ITaskAwareModelR
 			return name.includes('3.5') || name.includes('3.7') || name.includes('4') || name.includes('opus') || name.includes('sonnet');
 		}
 		if (provider === 'openai') {
-			return name.includes('4o') || name.includes('4.1') || name.includes('gpt-4');
+			// GPT-5 series (all variants support vision)
+			if (name.includes('gpt-5') || name.includes('gpt-5.1')) return true;
+			// GPT-4.1 series
+			if (name.includes('4.1')) return true;
+			// GPT-4o series
+			if (name.includes('4o')) return true;
+			// o-series reasoning models (o1, o3, o4-mini support vision)
+			if (name.startsWith('o1') || name.startsWith('o3') || name.startsWith('o4')) return true;
+			// Legacy GPT-4 models
+			if (name.includes('gpt-4')) return true;
+		}
+		if (provider === 'mistral') {
+			// Pixtral models support vision
+			if (name.includes('pixtral')) return true;
 		}
 		if (provider === 'ollama' || provider === 'vllm') {
 			return name.includes('llava') || name.includes('bakllava') || name.includes('vision');

src/vs/workbench/contrib/cortexide/common/routingSmokeTests.ts

@@ -174,11 +174,18 @@ async function testImageScreenshot(router: ITaskAwareModelRouter): Promise<Smoke
 
 	try {
 		const decision = await router.route(context);
-		const isVisionModel = decision.modelSelection.providerName.toLowerCase() === 'gemini' ||
-		                     decision.modelSelection.modelName.toLowerCase().includes('4o') ||
-		                     decision.modelSelection.modelName.toLowerCase().includes('4.1') ||
-		                     decision.modelSelection.modelName.toLowerCase().includes('claude') ||
-		                     decision.modelSelection.modelName.toLowerCase().includes('llava');
+		const modelName = decision.modelSelection.modelName.toLowerCase();
+		const provider = decision.modelSelection.providerName.toLowerCase();
+		const isVisionModel = provider === 'gemini' ||
+		                     modelName.includes('gpt-5') ||
+		                     modelName.includes('4.1') ||
+		                     modelName.includes('4o') ||
+		                     modelName.startsWith('o1') ||
+		                     modelName.startsWith('o3') ||
+		                     modelName.startsWith('o4') ||
+		                     modelName.includes('claude') ||
+		                     modelName.includes('pixtral') ||
+		                     modelName.includes('llava');
 
 		return {
 			name: 'Image screenshot',