diff --git a/Cargo.lock b/Cargo.lock
index 6e41156..93c3eee 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -720,6 +720,7 @@ version = "0.1.0"
 dependencies = [
  "anyhow",
  "config",
+ "dirs 5.0.1",
  "serde",
  "shellexpand",
  "thiserror 1.0.69",
diff --git a/crates/g3-config/Cargo.toml b/crates/g3-config/Cargo.toml
index bc9e7c1..d818d23 100644
--- a/crates/g3-config/Cargo.toml
+++ b/crates/g3-config/Cargo.toml
@@ -11,3 +11,4 @@ anyhow = { workspace = true }
 thiserror = { workspace = true }
 toml = "0.8"
 shellexpand = "3.0"
+dirs = "5.0"
diff --git a/crates/g3-config/src/lib.rs b/crates/g3-config/src/lib.rs
index 5b3596f..46856f9 100644
--- a/crates/g3-config/src/lib.rs
+++ b/crates/g3-config/src/lib.rs
@@ -71,6 +71,50 @@ impl Default for Config {
 
 impl Config {
     pub fn load(config_path: Option<&str>) -> Result<Self> {
+        // Check if any config file exists
+        let config_exists = if let Some(path) = config_path {
+            Path::new(path).exists()
+        } else {
+            // Check default locations
+            let default_paths = [
+                "./g3.toml",
+                "~/.config/g3/config.toml",
+                "~/.g3.toml",
+            ];
+            
+            default_paths.iter().any(|path| {
+                let expanded_path = shellexpand::tilde(path);
+                Path::new(expanded_path.as_ref()).exists()
+            })
+        };
+        
+        // If no config exists, create and save a default Qwen config
+        if !config_exists {
+            let qwen_config = Self::default_qwen_config();
+            
+            // Save to default location
+            let config_dir = dirs::home_dir()
+                .map(|mut path| {
+                    path.push(".config");
+                    path.push("g3");
+                    path
+                })
+                .unwrap_or_else(|| std::path::PathBuf::from("."));
+            
+            // Create directory if it doesn't exist
+            std::fs::create_dir_all(&config_dir).ok();
+            
+            let config_file = config_dir.join("config.toml");
+            if let Err(e) = qwen_config.save(config_file.to_str().unwrap()) {
+                eprintln!("Warning: Could not save default config: {}", e);
+            } else {
+                println!("Created default Qwen configuration at: {}", config_file.display());
+            }
+            
+            return Ok(qwen_config);
+        }
+        
+        // Existing config loading logic
         let mut settings = config::Config::builder();
         
         // Load default configuration
@@ -108,6 +152,30 @@ impl Config {
         Ok(config)
     }
     
+    fn default_qwen_config() -> Self {
+        Self {
+            providers: ProvidersConfig {
+                openai: None,
+                anthropic: None,
+                embedded: Some(EmbeddedConfig {
+                    model_path: "~/.cache/g3/models/qwen2.5-7b-instruct-q3_k_m.gguf".to_string(),
+                    model_type: "qwen".to_string(),
+                    context_length: Some(32768),  // Qwen2.5 supports 32k context
+                    max_tokens: Some(2048),
+                    temperature: Some(0.1),
+                    gpu_layers: Some(32),
+                    threads: Some(8),
+                }),
+                default_provider: "embedded".to_string(),
+            },
+            agent: AgentConfig {
+                max_context_length: 8192,
+                enable_streaming: true,
+                timeout_seconds: 60,
+            },
+        }
+    }
+    
     pub fn save(&self, path: &str) -> Result<()> {
         let toml_string = toml::to_string_pretty(self)?;
         std::fs::write(path, toml_string)?;
diff --git a/g3_session_hello_test_a63e133911916b31.json b/g3_session_hello_test_a63e133911916b31.json
new file mode 100644
index 0000000..d82cba3
--- /dev/null
+++ b/g3_session_hello_test_a63e133911916b31.json
@@ -0,0 +1,32 @@
+{
+  "context_window": {
+    "conversation_history": [
+      {
+        "content": "You are G3, a general-purpose AI agent. Your goal is to analyze and solve problems by writing code.\n\n# Tool Call Format\n\nWhen you need to execute a tool, write ONLY the JSON tool call on a new line:\n\n{\"tool\": \"tool_name\", \"args\": {\"param\": \"value\"}}\n\nThe tool will execute immediately and you'll receive the result (success or error) to continue with.\n\n# Available Tools\n\n- **shell**: Execute shell commands\n  - Format: {\"tool\": \"shell\", \"args\": {\"command\": \"your_command_here\"}}\n  - Example: {\"tool\": \"shell\", \"args\": {\"command\": \"ls ~/Downloads\"}}\n\n- **final_output**: Signal task completion with a detailed summary of work done in markdown format\n  - Format: {\"tool\": \"final_output\", \"args\": {\"summary\": \"what_was_accomplished\"}}\n\n# Instructions\n\n1. Analyze the request and break down into smaller tasks if appropriate\n2. Execute ONE tool at a time\n3. STOP when the original request was satisfied\n4. Call the final_output tool when done\n\n# Response Guidelines\n\n- Use Markdown formatting for all responses except tool calls.\n- Whenever taking actions, use the pronoun 'I'\n\n",
+        "role": "system"
+      },
+      {
+        "content": "Task: hello test",
+        "role": "user"
+      },
+      {
+        "content": "I will start by executing a simple task as requested. Let's print \"Hello, Test\" to confirm the task is understood and can be executed.\n\n{\"tool\": \"shell\", \"args\": {\"command\":\"echo Hello, Test\"}}",
+        "role": "assistant"
+      },
+      {
+        "content": "Tool result: Hello, Test",
+        "role": "user"
+      },
+      {
+        "content": "I will start by executing a simple task as requested. Let's print \"Hello, Test\" to confirm the task is understood and can be executed.\n\nTool executed: shell -> Hello, Test\n\n{\"tool\": \"final_output\", \"args\": {\"summary\": \"# Task Accomplished\n\nThe task 'hello test' was successfully executed. The output was:\n\n```\nHello, Test\n```\n\nThis confirms that the request was understood and completed as intended.\"}}",
+        "role": "assistant"
+      }
+    ],
+    "percentage_used": 0.9185791015625,
+    "total_tokens": 32768,
+    "used_tokens": 301
+  },
+  "session_id": "hello_test_a63e133911916b31",
+  "status": "completed",
+  "timestamp": 1757966669
+}
\ No newline at end of file