Auto-detect context window size from GGUF for embedded providers

- Add context_window_size() method to LLMProvider trait
- Implement for EmbeddedProvider to return the auto-detected context length
- Update Agent to query provider directly instead of using hardcoded defaults
- Removes need for model-specific context length mappings

crates/g3-providers/src/embedded.rs

@@ -700,6 +700,10 @@ impl LLMProvider for EmbeddedProvider {
     fn temperature(&self) -> f32 {
         self.temperature
     }
+
+    fn context_window_size(&self) -> Option<u32> {
+        Some(self.context_length)
+    }
 }
 
 #[cfg(test)]

crates/g3-providers/src/lib.rs

@@ -39,6 +39,12 @@ pub trait LLMProvider: Send + Sync {
 
     /// Get the configured temperature for this provider
     fn temperature(&self) -> f32;
+
+    /// Get the context window size for this provider
+    /// Returns None if the provider doesn't have a fixed context window
+    fn context_window_size(&self) -> Option<u32> {
+        None
+    }
 }
 
 #[derive(Debug, Clone, Serialize, Deserialize)]