feat: replaced ollama with litellm (#18)

Co-authored-by: Sharang Parnerkar <parnerkarsharang@gmail.com>
Reviewed-on: #18

src/models/provider.rs

@@ -3,8 +3,8 @@ use serde::{Deserialize, Serialize};
 /// Supported LLM provider backends.
 #[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
 pub enum LlmProvider {
-    /// Self-hosted models via Ollama
-    Ollama,
+    /// LiteLLM proxy for unified model access
+    LiteLlm,
     /// Hugging Face Inference API
     HuggingFace,
     /// OpenAI-compatible endpoints
@@ -17,7 +17,7 @@ impl LlmProvider {
     /// Returns the display name for a provider.
     pub fn label(&self) -> &'static str {
         match self {
-            Self::Ollama => "Ollama",
+            Self::LiteLlm => "LiteLLM",
             Self::HuggingFace => "Hugging Face",
             Self::OpenAi => "OpenAI",
             Self::Anthropic => "Anthropic",
@@ -29,7 +29,7 @@ impl LlmProvider {
 ///
 /// # Fields
 ///
-/// * `id` - Unique model identifier (e.g. "llama3.1:8b")
+/// * `id` - Unique model identifier (e.g. "qwen3-32b")
 /// * `name` - Human-readable display name
 /// * `provider` - Which provider hosts this model
 /// * `context_window` - Maximum context length in tokens
@@ -79,8 +79,8 @@ mod tests {
     use pretty_assertions::assert_eq;
 
     #[test]
-    fn llm_provider_label_ollama() {
-        assert_eq!(LlmProvider::Ollama.label(), "Ollama");
+    fn llm_provider_label_litellm() {
+        assert_eq!(LlmProvider::LiteLlm.label(), "LiteLLM");
     }
 
     #[test]
@@ -101,7 +101,7 @@ mod tests {
     #[test]
     fn llm_provider_serde_round_trip() {
         for variant in [
-            LlmProvider::Ollama,
+            LlmProvider::LiteLlm,
             LlmProvider::HuggingFace,
             LlmProvider::OpenAi,
             LlmProvider::Anthropic,
@@ -117,10 +117,10 @@ mod tests {
     #[test]
     fn model_entry_serde_round_trip() {
         let entry = ModelEntry {
-            id: "llama3.1:8b".into(),
-            name: "Llama 3.1 8B".into(),
-            provider: LlmProvider::Ollama,
-            context_window: 8192,
+            id: "qwen3-32b".into(),
+            name: "Qwen3 32B".into(),
+            provider: LlmProvider::LiteLlm,
+            context_window: 32,
         };
         let json = serde_json::to_string(&entry).expect("serialize ModelEntry");
         let back: ModelEntry = serde_json::from_str(&json).expect("deserialize ModelEntry");