🔧 Fix Token Limits & Invalid JSON Response Errors (#1934)

ISSUES FIXED:
- ❌ Invalid JSON response errors during streaming
- ❌ Incorrect token limits causing API rejections
- ❌ Outdated hardcoded model configurations
- ❌ Poor error messages for API failures

SOLUTIONS IMPLEMENTED:

🎯 ACCURATE TOKEN LIMITS & CONTEXT SIZES
- OpenAI GPT-4o: 128k context (was 8k)
- OpenAI GPT-3.5-turbo: 16k context (was 8k)
- Anthropic Claude 3.5 Sonnet: 200k context (was 8k)
- Anthropic Claude 3 Haiku: 200k context (was 8k)
- Google Gemini 1.5 Pro: 2M context (was 8k)
- Google Gemini 1.5 Flash: 1M context (was 8k)
- Groq Llama models: 128k context (was 8k)
- Together models: Updated with accurate limits

�� DYNAMIC MODEL FETCHING ENHANCED
- Smart context detection from provider APIs
- Automatic fallback to known limits when API unavailable
- Safety caps to prevent token overflow (100k max)
- Intelligent model filtering and deduplication

🛡️ IMPROVED ERROR HANDLING
- Specific error messages for Invalid JSON responses
- Token limit exceeded warnings with solutions
- API key validation with clear guidance
- Rate limiting detection and user guidance
- Network timeout handling

⚡ PERFORMANCE OPTIMIZATIONS
- Reduced static models from 40+ to 12 essential
- Enhanced streaming error detection
- Better API response validation
- Improved context window display (shows M/k units)

🔧 TECHNICAL IMPROVEMENTS
- Dynamic model context detection from APIs
- Enhanced streaming reliability
- Better token limit enforcement
- Comprehensive error categorization
- Smart model validation before API calls

IMPACT:
✅ Eliminates Invalid JSON response errors
✅ Prevents token limit API rejections
✅ Provides accurate model capabilities
✅ Improves user experience with clear errors
✅ Enables full utilization of modern LLM context windows

app/lib/modules/llm/providers/openai.ts

@@ -13,11 +13,14 @@ export default class OpenAIProvider extends BaseProvider {
   };
 
   staticModels: ModelInfo[] = [
-    { name: 'gpt-4o', label: 'GPT-4o', provider: 'OpenAI', maxTokenAllowed: 8000 },
-    { name: 'gpt-4o-mini', label: 'GPT-4o Mini', provider: 'OpenAI', maxTokenAllowed: 8000 },
-    { name: 'gpt-4-turbo', label: 'GPT-4 Turbo', provider: 'OpenAI', maxTokenAllowed: 8000 },
-    { name: 'gpt-4', label: 'GPT-4', provider: 'OpenAI', maxTokenAllowed: 8000 },
-    { name: 'gpt-3.5-turbo', label: 'GPT-3.5 Turbo', provider: 'OpenAI', maxTokenAllowed: 8000 },
+    /*
+     * Essential fallback models - only the most stable/reliable ones
+     * GPT-4o: 128k context, high performance, recommended for most tasks
+     */
+    { name: 'gpt-4o', label: 'GPT-4o', provider: 'OpenAI', maxTokenAllowed: 128000 },
+
+    // GPT-3.5-turbo: 16k context, fast and cost-effective
+    { name: 'gpt-3.5-turbo', label: 'GPT-3.5 Turbo', provider: 'OpenAI', maxTokenAllowed: 16000 },
   ];
 
   async getDynamicModels(
@@ -53,12 +56,30 @@ export default class OpenAIProvider extends BaseProvider {
         !staticModelIds.includes(model.id),
     );
 
-    return data.map((m: any) => ({
-      name: m.id,
-      label: `${m.id}`,
-      provider: this.name,
-      maxTokenAllowed: m.context_window || 32000,
-    }));
+    return data.map((m: any) => {
+      // Get accurate context window from OpenAI API
+      let contextWindow = 32000; // default fallback
+
+      // OpenAI provides context_length in their API response
+      if (m.context_length) {
+        contextWindow = m.context_length;
+      } else if (m.id?.includes('gpt-4o')) {
+        contextWindow = 128000; // GPT-4o has 128k context
+      } else if (m.id?.includes('gpt-4-turbo') || m.id?.includes('gpt-4-1106')) {
+        contextWindow = 128000; // GPT-4 Turbo has 128k context
+      } else if (m.id?.includes('gpt-4')) {
+        contextWindow = 8192; // Standard GPT-4 has 8k context
+      } else if (m.id?.includes('gpt-3.5-turbo')) {
+        contextWindow = 16385; // GPT-3.5-turbo has 16k context
+      }
+
+      return {
+        name: m.id,
+        label: `${m.id} (${Math.floor(contextWindow / 1000)}k context)`,
+        provider: this.name,
+        maxTokenAllowed: Math.min(contextWindow, 128000), // Cap at 128k for safety
+      };
+    });
   }
 
   getModelInstance(options: {