Increase LiteLLM request timeout from 60s to 180s

The askash-main model at llm.nxtgauge.com takes 60-120s to generate
job descriptions; previous 60s timeout caused all JD generations to fail.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

apps/users/src/litellm.rs

@@ -82,7 +82,7 @@ pub async fn call_litellm(
     max_tokens: Option<i32>,
 ) -> Result<LiteLLMResponse, String> {
     let client = reqwest::Client::builder()
-        .timeout(std::time::Duration::from_secs(60))
+        .timeout(std::time::Duration::from_secs(180))
         .build()
         .map_err(|e| format!("Failed to build HTTP client: {}", e))?;
 
@@ -138,7 +138,7 @@ pub async fn call_litellm_with_system(
     max_tokens: Option<i32>,
 ) -> Result<LiteLLMResponse, String> {
     let client = reqwest::Client::builder()
-        .timeout(std::time::Duration::from_secs(60))
+        .timeout(std::time::Duration::from_secs(180))
         .build()
         .map_err(|e| format!("Failed to build HTTP client: {}", e))?;