chore: update all grok-2 references to grok-4

README.md

@@ -9,7 +9,7 @@ A unified, high-performance LLM proxy gateway built in Go. It provides a single
   - **OpenAI:** GPT-4o, GPT-4o Mini, o1, o3 reasoning models.
   - **Google Gemini:** Gemini 2.0 Flash, Pro, and vision models (with native CoT support).
   - **DeepSeek:** DeepSeek Chat and Reasoner (R1) models.
-  - **xAI Grok:** Grok-2 models.
+  - **xAI Grok:** Grok-4 models.
   - **Ollama:** Local LLMs running on your network.
 - **Observability & Tracking:**
   - **Asynchronous Logging:** Non-blocking request logging to SQLite using background workers.

internal/config/config.go

@@ -99,7 +99,7 @@ func Load() (*Config, error) {
 
 	v.SetDefault("providers.grok.api_key_env", "GROK_API_KEY")
 	v.SetDefault("providers.grok.base_url", "https://api.x.ai/v1")
-	v.SetDefault("providers.grok.default_model", "grok-2")
+	v.SetDefault("providers.grok.default_model", "grok-4-1-fast-non-reasoning")
 	v.SetDefault("providers.grok.enabled", true)
 
 	v.SetDefault("providers.ollama.base_url", "http://localhost:11434/v1")

static/js/pages/monitoring.js

@@ -492,7 +492,7 @@ class MonitoringPage {
     simulateRequest() {
         const clients = ['client-1', 'client-2', 'client-3', 'client-4', 'client-5'];
         const providers = ['OpenAI', 'Gemini', 'DeepSeek', 'Grok'];
-        const models = ['gpt-4o', 'gpt-4o-mini', 'gemini-2.0-flash', 'deepseek-chat', 'grok-2'];
+        const models = ['gpt-4o', 'gpt-4o-mini', 'gemini-2.0-flash', 'deepseek-chat', 'grok-4-1-fast-non-reasoning'];
         const statuses = ['success', 'success', 'success', 'error', 'warning']; // Mostly success
         
         const request = {