feat(lsp): implement LSP client and server management

- Added LspClient for handling communication with LSP servers, including methods for initialization, notifications, and requests.
- Introduced LspManager to manage multiple LSP server connections, allowing for connection, disconnection, and retrieval of server capabilities.
- Created tools for connecting to LSP servers, retrieving diagnostics, hover information, code completion, definitions, and references.
- Enhanced UI rendering to display token usage and settings in the overlay.
- Updated status bar to show current token usage and selected provider/model.

src/model/app_config.rs

@@ -12,6 +12,7 @@ pub struct AppConfig {
     pub model_roles: HashMap<String, ModelRole>,
     pub default_provider: String,
     pub default_model: String,
+    pub default_context_window: u32,
 }
 
 /// Connection details for a single LLM provider (base URL, API key source).
@@ -30,6 +31,7 @@ pub struct ModelRole {
     pub provider: String,
     pub model: String,
     pub max_tokens: Option<u32>,
+    pub context_window: Option<u32>,
     pub temperature: Option<f32>,
 }
 
@@ -52,7 +54,8 @@ impl Default for AppConfig {
         model_roles.insert("default".to_string(), ModelRole {
             provider: "zen".to_string(),
             model: "deepseek-v4-flash-free".to_string(),
-            max_tokens: Some(8192),
+            max_tokens: None,
+            context_window: None,
             temperature: Some(0.7),
         });
         AppConfig {
@@ -60,6 +63,7 @@ impl Default for AppConfig {
             model_roles,
             default_provider: "zen".to_string(),
             default_model: "deepseek-v4-flash-free".to_string(),
+            default_context_window: 256_000,
         }
     }
 }

src/model/conversation.rs

@@ -10,8 +10,8 @@ pub struct Conversation {
     pub system_prompt: String,
     pub session_id: String,
     pub model: String,
-    pub max_tokens: u32,
-    pub temperature: f32,
+    pub max_tokens: Option<u32>,
+    pub temperature: Option<f32>,
 }
 
 impl Conversation {
@@ -23,8 +23,8 @@ impl Conversation {
             system_prompt,
             session_id,
             model: "anthropic/claude-opus-4-8".to_string(),
-            max_tokens: 8192,
-            temperature: 0.7,
+            max_tokens: None,
+            temperature: None,
         }
     }
 

src/model/settings.rs

@@ -31,8 +31,8 @@ pub struct Settings {
     pub provider: String,
     pub model: String,
     pub api_keys: std::collections::HashMap<String, String>,
-    pub max_tokens: u32,
-    pub temperature: f32,
+    pub max_tokens: Option<u32>,
+    pub temperature: Option<f32>,
     pub review_enabled: bool,
     pub review_max_lessons_per_run: usize,
     pub adaptive_review_max_skip: u32,
@@ -49,8 +49,8 @@ impl Default for Settings {
             provider: "zen".to_string(),
             model: "deepseek-v4-flash-free".to_string(),
             api_keys: std::collections::HashMap::new(),
-            max_tokens: 8192,
-            temperature: 0.7,
+            max_tokens: None,
+            temperature: None,
             review_enabled: true,
             review_max_lessons_per_run: 5,
             adaptive_review_max_skip: 3,